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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transformation or change in states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arton
    -0.16
    allis
    -0.15
    dent
    -0.15
    olute
    -0.14
    sis
    -0.14
    unga
    -0.14
    _BC
    -0.14
    çĹĩ
    -0.14
    ;element
    -0.14
    pong
    -0.14
    POSITIVE LOGITS
    aily
    0.15
    Ĥ¨
    0.15
     Scal
    0.15
    von
    0.14
    ible
    0.14
     Shen
    0.14
     timber
    0.14
     hed
    0.13
    ub
    0.13
    FormField
    0.13
    Act Density 0.327%

    No Known Activations