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

    Neuronpedia

    INDEX
    Explanations

    references to software libraries or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deaux
    -0.17
    iger
    -0.15
    opensource
    -0.15
    ivant
    -0.15
    dale
    -0.15
     Surveillance
    -0.14
     Bath
    -0.14
    abar
    -0.14
    IDEOS
    -0.14
    áÅĻ
    -0.13
    POSITIVE LOGITS
    _GRAY
    0.15
    oston
    0.14
     firmly
    0.14
     Garr
    0.14
     transf
    0.14
    ustry
    0.14
    ement
    0.13
     Merc
    0.13
    ICON
    0.13
     surrogate
    0.13
    Act Density 0.000%

    No Known Activations