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

    Neuronpedia

    INDEX
    Explanations

    phrases related to anticipation or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipl
    -0.14
    addtogroup
    -0.14
    iqueta
    -0.14
     Essentials
    -0.13
    Ä±ÅŁÄ±k
    -0.13
    quential
    -0.13
    ÙĦÙĥ
    -0.13
     rast
    -0.13
    elve
    -0.13
    ulfill
    -0.12
    POSITIVE LOGITS
     how
    0.60
     what
    0.52
    how
    0.46
     why
    0.45
    what
    0.41
     where
    0.40
     cómo
    0.35
     whom
    0.35
     How
    0.35
     who
    0.35
    Act Density 0.086%

    No Known Activations