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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing expectations or predictions about events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vale
    -0.16
    cation
    -0.15
    arkin
    -0.15
    chrift
    -0.14
     fileInfo
    -0.14
    oller
    -0.14
     gratuitement
    -0.13
    .Actor
    -0.13
    neas
    -0.13
    dB
    -0.13
    POSITIVE LOGITS
    icone
    0.17
    ¾
    0.15
    ÃĹ↵↵
    0.15
    445
    0.15
    Äĥng
    0.14
    _TOUCH
    0.14
    -regexp
    0.13
    âng
    0.13
    .lazy
    0.13
    ROTO
    0.13
    Act Density 0.022%

    No Known Activations