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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate necessity or obligation

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

    "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jaket
    -0.43
     programmation
    -0.42
     proyec
    -0.40
     fisuras
    -0.39
    RegressionTest
    -0.38
     niega
    -0.38
     anillos
    -0.37
     neige
    -0.35
     Ganzen
    -0.35
     imágen
    -0.35
    POSITIVE LOGITS
     Must
    0.89
    Must
    0.89
     Gotta
    0.78
     must
    0.78
     Надо
    0.75
    gotta
    0.75
    must
    0.73
     fallu
    0.72
    Gotta
    0.71
     phải
    0.71
    Act Density 0.077%

    No Known Activations