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

    Neuronpedia

    INDEX
    Explanations

    references to regulated environments or guidelines related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibia
    -0.15
    amber
    -0.15
    orda
    -0.15
    æķĻ
    -0.14
    moid
    -0.14
    IDL
    -0.14
    ernen
    -0.13
     пеÑĢеÑģ
    -0.13
    .dds
    -0.13
    .fit
    -0.13
    POSITIVE LOGITS
    åĢī
    0.18
    aston
    0.17
    .habbo
    0.15
    ignite
    0.15
     whose
    0.14
     otherwise
    0.14
    adle
    0.14
     which
    0.13
    Equip
    0.13
    ogn
    0.13
    Act Density 0.228%

    No Known Activations