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

    Neuronpedia

    INDEX
    Explanations

    connections and interactions between entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.07
    3:0.08
    4:0.16
    5:0.02
    6:0.03
    7:0.35
    8:0.03
    9:0.03
    10:0.08
    11:0.08
    Negative Logits
     proportion
    -1.72
    iameter
    -1.52
     measure
    -1.47
     diameter
    -1.46
    strings
    -1.46
    quant
    -1.43
     emphasis
    -1.43
     stemmed
    -1.41
    currency
    -1.41
     tide
    -1.40
    POSITIVE LOGITS
     prostitutes
    1.65
    Agent
    1.63
     Slaughter
    1.53
    irlf
    1.52
    ournal
    1.42
     Sleeping
    1.42
     fellow
    1.42
     befriend
    1.40
     sophistic
    1.39
     Enemy
    1.38
    Act Density 0.001%

    No Known Activations