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

    Neuronpedia

    INDEX
    Explanations

    affirmations or expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newBuilder
    -0.61
    ReusableCell
    -0.58
     Roskov
    -0.57
    ########.
    -0.55
    tvguidetime
    -0.54
    fromnode
    -0.54
    intios
    -0.53
    //
    -0.52
    PROLOG
    -0.50
    ఞ
    -0.50
    POSITIVE LOGITS
    lahoma
    0.71
    LAHOMA
    0.69
     boomer
    0.68
    ays
    0.66
     fine
    0.66
    enough
    0.61
     enough
    0.59
     Boomer
    0.57
     FINE
    0.57
     Corral
    0.57
    Act Density 0.152%

    No Known Activations