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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases that signal personal experiences or confessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingen
    -0.18
    etail
    -0.17
    lect
    -0.17
    erno
    -0.17
    967
    -0.15
    ledge
    -0.15
    åĻ
    -0.14
    orr
    -0.14
    ef
    -0.14
    ides
    -0.14
    POSITIVE LOGITS
     fairness
    0.17
    dden
    0.16
     related
    0.16
     unrelated
    0.15
    tiler
    0.15
    AINS
    0.15
    stagram
    0.15
    zcze
    0.15
    deen
    0.14
    utra
    0.14
    Act Density 0.108%

    No Known Activations