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

    Neuronpedia

    INDEX
    Explanations

    specific elements relating to user interaction or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culus
    -0.15
    ximity
    -0.15
    alleries
    -0.14
    anki
    -0.14
    unkt
    -0.14
    สร
    -0.14
    utz
    -0.14
     somehow
    -0.14
    _targets
    -0.14
    igram
    -0.14
    POSITIVE LOGITS
    ame
    0.15
    abet
    0.15
     redhead
    0.15
    lets
    0.15
    _DEFIN
    0.15
    /cop
    0.15
    eum
    0.15
     Uph
    0.14
    ız
    0.14
     αδ
    0.14
    Act Density 0.001%

    No Known Activations