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

    Neuronpedia

    INDEX
    Explanations

    commands or imperatives in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.10
    3:0.10
    4:0.08
    5:0.08
    6:0.05
    7:0.08
    8:0.07
    9:0.06
    10:0.10
    11:0.08
    Negative Logits
    sand
    -2.09
    uum
    -2.02
     Squid
    -1.94
    Clean
    -1.91
    Salt
    -1.88
    モ
    -1.86
     Sponge
    -1.86
     Elementary
    -1.85
    プ
    -1.85
    パ
    -1.79
    POSITIVE LOGITS
    latest
    2.07
    aimon
    1.91
    inav
    1.90
    iffe
    1.82
    oleon
    1.82
    leeve
    1.80
    ographies
    1.79
    ails
    1.79
    cano
    1.77
    atton
    1.76
    Act Density 0.000%

    No Known Activations