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

    Neuronpedia

    INDEX
    Explanations

    words expressing strong opinions or judgments, particularly in a derogatory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.63
    \{\\
    -0.61
     snippetHide
    -0.58
     Robert
    -0.49
     Syrie
    -0.47
    وروبا
    -0.47
    agues
    -0.46
    obile
    -0.46
    True
    -0.46
     garantire
    -0.46
    POSITIVE LOGITS
    FunctionFlags
    0.66
    uxxxx
    0.60
    ConstraintMaker
    0.58
     estekak
    0.58
     ویکی‌پدیای
    0.58
    PYX
    0.55
    ViewFeatures
    0.55
     VIAF
    0.55
    DIPSETTING
    0.53
    PhysRevD
    0.52
    Act Density 0.645%

    No Known Activations