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

    Neuronpedia

    INDEX
    Explanations

    words related to titles or naming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crackers
    -0.16
    kus
    -0.15
    еÑĦ
    -0.15
    clave
    -0.15
    urgeon
    -0.14
    PCS
    -0.14
    jej
    -0.14
    icorn
    -0.14
    aspers
    -0.14
    emer
    -0.13
    POSITIVE LOGITS
    ahl
    0.17
     equivalents
    0.16
    rop
    0.15
    ANGUAGE
    0.15
    asy
    0.15
    ium
    0.14
    inary
    0.14
    atat
    0.14
    aryl
    0.14
    ameda
    0.14
    Act Density 0.002%

    No Known Activations