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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical or emotional states or actions

    oai_token-act-pair · gpt-3.5-turbo

    words associated with positive and negative traits or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.65
    éļ
    -0.64
    audi
    -0.61
     bene
    -0.61
     Luxem
    -0.59
     entirety
    -0.59
     ascertain
    -0.58
     wil
    -0.58
    other
    -0.56
     Neurolog
    -0.55
    POSITIVE LOGITS
     quicker
    0.93
     ASAP
    0.85
     quickly
    0.85
     again
    0.84
     traction
    0.82
     faster
    0.77
     sooner
    0.77
    */(
    0.75
    quick
    0.74
     puberty
    0.73
    Act Density 0.193%

    No Known Activations