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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to evidence and validation of claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.10
    2:0.03
    3:0.03
    4:0.03
    5:0.40
    6:0.03
    7:0.02
    8:0.09
    9:0.05
    10:0.07
    11:0.04
    Negative Logits
    achine
    -1.70
    Hen
    -1.65
     Patri
    -1.62
    rus
    -1.59
    xi
    -1.57
    ula
    -1.56
    eli
    -1.55
    Anth
    -1.55
     Dogs
    -1.53
    Dog
    -1.49
    POSITIVE LOGITS
     unaccount
    2.21
    existent
    1.80
     unlaw
    1.80
     removable
    1.75
     rul
    1.74
     requirement
    1.73
     notor
    1.71
     Flavoring
    1.67
     residual
    1.67
    functional
    1.66
    Act Density 0.538%

    No Known Activations