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

    Neuronpedia

    INDEX
    Explanations

    terms associated with involvement or engagement in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evin
    -0.16
    ÑĥÑī
    -0.16
    pite
    -0.15
    .IsNull
    -0.15
    drž
    -0.14
    teÅŁ
    -0.14
    trimmed
    -0.14
    UniformLocation
    -0.14
    гл
    -0.14
    ections
    -0.14
    POSITIVE LOGITS
     Gone
    0.17
    elen
    0.15
    AD
    0.15
    quette
    0.15
    arez
    0.14
    âng
    0.14
     è¡
    0.14
    EP
    0.14
    ONA
    0.14
    dere
    0.14
    Act Density 0.000%

    No Known Activations