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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tracking and locating something or someone

    oai_token-act-pair · gpt-3.5-turbo

    words related to monitoring or following subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.77
    Hom
    -0.66
    AIN
    -0.66
     Harbor
    -0.65
    lied
    -0.64
    ahu
    -0.64
    bery
    -0.63
    ammy
    -0.61
    hedon
    -0.60
     Prelude
    -0.60
    POSITIVE LOGITS
     down
    0.99
    down
    0.85
     developments
    0.80
     closely
    0.80
    DOWN
    0.79
    downs
    0.78
    enance
    0.75
     movements
    0.74
    llah
    0.72
     trends
    0.72
    Act Density 0.056%

    No Known Activations