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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removing or eliminating something

    oai_token-act-pair · gpt-3.5-turbo

    phrases about removing or eliminating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mpeg
    -0.73
    NG
    -0.67
     Sop
    -0.66
    NZ
    -0.64
    Irish
    -0.64
    Led
    -0.63
    LAN
    -0.63
    DOC
    -0.62
    BE
    -0.62
    Ko
    -0.62
    POSITIVE LOGITS
    anium
    0.88
    itaire
    0.88
    uations
    0.88
    ged
    0.87
    ges
    0.87
    icide
    0.83
    osaurus
    0.82
    ings
    0.81
    ients
    0.81
    uation
    0.80
    Act Density 0.017%

    No Known Activations