Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    contact information related to law enforcement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to crime reporting and police contact methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.10
    2:0.09
    3:0.08
    4:0.08
    5:0.09
    6:0.07
    7:0.06
    8:0.07
    9:0.14
    10:0.08
    11:0.04
    Negative Logits
     virtues
    -1.43
     physicists
    -1.35
     conson
    -1.34
     goose
    -1.33
     principle
    -1.32
     intuition
    -1.29
     calculus
    -1.25
     resh
    -1.25
     prag
    -1.25
     philosophers
    -1.24
    POSITIVE LOGITS
    ounty
    1.55
     Crim
    1.53
    police
    1.49
    nsics
    1.48
    escal
    1.47
    license
    1.44
    crime
    1.44
    arnaev
    1.41
    aqu
    1.40
     Parking
    1.40
    Act Density 0.005%

    No Known Activations