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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to system processes or mechanisms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dynamics and mechanisms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umper
    -0.73
    atory
    -0.70
    inis
    -0.70
    fires
    -0.69
    este
    -0.68
    ificant
    -0.68
    leased
    -0.67
    leck
    -0.67
    wra
    -0.67
    --+
    -0.67
    POSITIVE LOGITS
    odynamics
    0.88
     dictates
    0.81
    models
    0.77
    chool
    0.76
     surrounding
    0.75
     collide
    0.73
     equations
    0.73
     prevail
    0.73
     equation
    0.71
    hare
    0.70
    Act Density 0.081%

    No Known Activations