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

    Neuronpedia

    INDEX
    Explanations

    evidence related to sexual harassment allegations and workplace misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.77
     &___
    -0.61
    )."
    -0.61
    SharedDtor
    -0.57
    )"
    -0.56
     дописавши
    -0.55
     surla
    -0.55
     سكانية
    -0.54
    "]))
    -0.53
    >()
    -0.52
    POSITIVE LOGITS
    2.85
    ↵
    1.56
     

    1.33
    _

    1.28
    .

    1.28
    /

    1.25
    ?

    1.25
    !

    1.23
    []

    1.21
    ,

    1.17
    Act Density 0.172%
    No Known Activations