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

    Neuronpedia

    INDEX
    Explanations

    verbs relating to prevention or hindrance

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to preventing or stopping events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.81
    geist
    -0.80
    enegger
    -0.79
    framework
    -0.77
    elt
    -0.74
    bard
    -0.73
    stand
    -0.67
    spirit
    -0.66
    bold
    -0.64
    Lenin
    -0.63
    POSITIVE LOGITS
    ative
    0.94
     regress
    0.92
     detection
    0.90
     accidental
    0.88
     pregnancies
    0.87
     duplication
    0.84
     duplicate
    0.84
     future
    0.83
     accidents
    0.81
     extradition
    0.79
    Act Density 0.044%

    No Known Activations