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

    Neuronpedia

    INDEX
    Explanations

    words related to personal interactions and pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Threshold
    -0.17
    sq
    -0.15
     vil
    -0.15
    VAS
    -0.14
    threshold
    -0.14
    å´
    -0.14
     Crosby
    -0.13
    Threshold
    -0.13
     pan
    -0.13
     Coleman
    -0.13
    POSITIVE LOGITS
    ufen
    0.17
    ÂĽ
    0.15
    nger
    0.15
    roupe
    0.14
    istra
    0.14
    онов
    0.14
    juana
    0.14
     traffic
    0.14
    arin
    0.14
    azing
    0.14
    Act Density 0.000%

    No Known Activations