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

    Neuronpedia

    INDEX
    Explanations

    evidence of vulnerable populations and related social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.06
    2:0.14
    3:0.07
    4:0.02
    5:0.06
    6:0.10
    7:0.11
    8:0.11
    9:0.09
    10:0.10
    11:0.07
    Negative Logits
     Illum
    -1.03
    yles
    -0.97
     Sgt
    -0.96
     Salt
    -0.96
     McCl
    -0.95
     Twain
    -0.93
    istries
    -0.93
     Desmond
    -0.91
     Darrell
    -0.90
     Saras
    -0.90
    POSITIVE LOGITS
    ealous
    1.23
    proven
    1.14
    ogeneous
    1.09
    stellar
    1.03
     snowball
    1.01
    criminal
    0.98
    .}
    0.98
    cffff
    0.98
    igent
    0.98
     pathological
    0.97
    Act Density 0.415%

    No Known Activations