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

    Neuronpedia

    INDEX
    Explanations

    phrases related to prevention

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to preventing negative outcomes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.92
    geist
    -0.76
    enegger
    -0.72
    elt
    -0.69
    stand
    -0.68
    etics
    -0.67
    edded
    -0.66
    eah
    -0.66
    bold
    -0.65
    night
    -0.63
    POSITIVE LOGITS
    ative
    0.95
     detection
    0.80
     regress
    0.80
    ively
    0.77
     pregnancies
    0.77
     duplicate
    0.75
     accidental
    0.74
     bothering
    0.74
     pregnancy
    0.72
     obstruct
    0.72
    Act Density 0.043%

    No Known Activations