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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals associated with politics or current affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antro
    -0.17
     itself
    -0.14
    oretical
    -0.14
    aroo
    -0.14
    dbg
    -0.13
    .fm
    -0.13
    quel
    -0.13
    egend
    -0.13
    azzi
    -0.13
    aan
    -0.13
    POSITIVE LOGITS
     Jr
    0.28
    çĪµ
    0.23
    åįļ士
    0.19
     himself
    0.18
    nesty
    0.18
     jr
    0.17
     who
    0.17
    who
    0.17
     III
    0.16
     PhD
    0.15
    Act Density 0.829%

    No Known Activations