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

    Neuronpedia

    INDEX
    Explanations

    key terms related to specific entities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endi
    -0.15
    rade
    -0.15
    inte
    -0.14
    egie
    -0.14
    antan
    -0.14
    uhe
    -0.14
    _rc
    -0.14
    ofire
    -0.14
    weg
    -0.13
     ADVISED
    -0.13
    POSITIVE LOGITS
    ModelProperty
    0.19
    deaux
    0.15
     paddle
    0.15
    HasKey
    0.14
    ipc
    0.14
     Leban
    0.14
    .ix
    0.13
     bekl
    0.13
    Bias
    0.13
    /shop
    0.13
    Act Density 0.048%

    No Known Activations