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

    Neuronpedia

    INDEX
    Explanations

    numeric identifiers or codes within a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wear
    -0.17
    ful
    -0.16
    get
    -0.16
    izon
    -0.15
     present
    -0.15
    reau
    -0.15
    707
    -0.15
     presence
    -0.14
     marsh
    -0.14
     Behavior
    -0.14
    POSITIVE LOGITS
    deÅŁ
    0.16
     ëħ¸ì¶ľ
    0.16
     OMIT
    0.16
    ÏģÏĩ
    0.14
    aversable
    0.14
    å¥ı
    0.14
    /cop
    0.14
    ÅĦst
    0.14
     vacc
    0.14
    ','=',
    0.14
    Act Density 0.022%

    No Known Activations