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

    Neuronpedia

    INDEX
    Explanations

    terms related to voluntary and involuntary actions or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /sm
    -0.19
    undry
    -0.18
    lei
    -0.16
    asper
    -0.15
    asu
    -0.14
     Joi
    -0.14
    æĵļ
    -0.14
    Ùıر
    -0.14
    thur
    -0.14
    ier
    -0.14
    POSITIVE LOGITS
    /random
    0.23
    mente
    0.21
    ously
    0.20
    ities
    0.20
    ely
    0.20
    aly
    0.19
    aneously
    0.19
    ness
    0.18
     nature
    0.18
     olarak
    0.17
    Act Density 0.091%

    No Known Activations