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

    Neuronpedia

    INDEX
    Explanations

    names of people or figures associated with specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anst
    -0.13
    enson
    -0.13
    _PAD
    -0.13
     fame
    -0.13
    azard
    -0.13
     Giles
    -0.13
    union
    -0.12
    ãĥ¬ãĥ¼
    -0.12
    agit
    -0.12
    ernal
    -0.12
    POSITIVE LOGITS
    tek
    0.14
     scrut
    0.13
    dob
    0.13
    ınca
    0.12
    liÄį
    0.12
    ëĭ´
    0.12
     navr
    0.12
    .scalablytyped
    0.12
    تب
    0.12
     bdsm
    0.12
    Act Density 0.123%

    No Known Activations