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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or expressions of dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text following hyphens or dashes

    np_acts-logits-general · gemini-2.0-flash

    hyphen followed by common tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.85
    (
    -0.65
     van
    -0.58
    ,
    -0.57
    Rüyada
    -0.56
    ielli
    -0.56
     Pritchard
    -0.56
     Kirkpatrick
    -0.56
     org
    -0.56
    "
    -0.53
    POSITIVE LOGITS
    *-
    0.99
    &-
    0.97
    =-=-=-=-
    0.95
    *-*-
    0.93
    =-=-
    0.92
     للمعارف
    0.87
    tvguidetime
    0.86
    ########.
    0.84
     ujednoznacz
    0.83
     itſelf
    0.82
    Act Density 1.296%

    No Known Activations