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

    Neuronpedia

    INDEX
    Explanations

    direct speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     colorful
    -0.16
    aph
    -0.15
     Naz
    -0.15
    avor
    -0.14
    alu
    -0.14
     Cycl
    -0.14
    _INS
    -0.14
    Obviously
    -0.14
    uteur
    -0.14
     basically
    -0.14
    POSITIVE LOGITS
    "default
    0.15
    strup
    0.15
     desar
    0.15
    _None
    0.15
     arter
    0.15
    loub
    0.14
    redo
    0.14
    .want
    0.14
     uncert
    0.14
     folk
    0.14
    Act Density 0.159%

    No Known Activations