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

    Neuronpedia

    INDEX
    Explanations

    monetary values and indicators of significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pring
    -0.84
    hower
    -0.84
    ovan
    -0.83
    othing
    -0.81
    asio
    -0.81
    oppable
    -0.80
    umblr
    -0.78
    omsky
    -0.77
    hod
    -0.76
    agons
    -0.75
    POSITIVE LOGITS
     Vanguard
    0.68
    ahime
    0.68
     Islands
    0.66
     Makoto
    0.65
    å¸
    0.63
     Kingdoms
    0.63
     Torres
    0.63
     Miy
    0.60
     Mann
    0.60
    ŃĶ
    0.59
    Act Density 0.014%

    No Known Activations