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

    Neuronpedia

    INDEX
    Explanations

    references to significant monetary values or high-value items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Larkin
    -0.73
     MART
    -0.71
     CM
    -0.69
     Rudd
    -0.68
    MART
    -0.66
     Lakewood
    -0.66
     Martini
    -0.66
     Mart
    -0.66
     Kearney
    -0.65
    jard
    -0.65
    POSITIVE LOGITS
     ACC
    0.91
    ACC
    0.79
     Acc
    0.77
     Croydon
    0.73
     McCain
    0.73
     Ridge
    0.69
     RIDGE
    0.67
     Lyle
    0.67
     Pam
    0.65
    acc
    0.64
    Act Density 1.562%

    No Known Activations