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

    Neuronpedia

    INDEX
    Explanations

    verbs related to ethical behavior and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.80
     NgModule
    -0.64
    fony
    -0.58
    󠁿
    -0.56
    chiato
    -0.56
    сім
    -0.55
    Даль
    -0.54
     proszę
    -0.54
     BNF
    -0.54
    AutoScale
    -0.53
    POSITIVE LOGITS
    ness
    0.75
     implementing
    0.69
     acquiring
    0.68
     obtaining
    0.67
     maintaining
    0.65
     Maintaining
    0.65
     oneself
    0.62
    мерть
    0.62
    Maintaining
    0.62
     concentrating
    0.61
    Act Density 0.476%

    No Known Activations