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

    Neuronpedia

    INDEX
    Explanations

    terms related to environment and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olum
    -0.16
    ẻ
    -0.16
    alore
    -0.16
    agara
    -0.16
     nud
    -0.15
    ooks
    -0.15
    atsu
    -0.15
    apest
    -0.14
    oad
    -0.14
    첨ë¶Ģ
    -0.14
    POSITIVE LOGITS
    ç¦ģ
    0.15
     Purpose
    0.14
    mas
    0.14
     Moo
    0.14
    Im
    0.14
    彦
    0.14
    usher
    0.14
     whites
    0.14
     mean
    0.13
    ause
    0.13
    Act Density 0.049%

    No Known Activations