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

    Neuronpedia

    INDEX
    Explanations

    future actions or intentions indicated by the phrase "going to."

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

    "to be" or "to [verb]"

    np_acts-logits-general · gemini-2.0-flash

    future action intentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.72
     bahkan
    -0.70
    rsiniz
    -0.65
     ikkje
    -0.60
    ſelves
    -0.57
     ikke
    -0.57
    ГЛА
    -0.57
     InputDecoration
    -0.57
    BagConstraints
    -0.57
    それも
    -0.57
    POSITIVE LOGITS
     be
    0.89
     GONNA
    0.64
     need
    0.63
    Gonna
    0.63
    MigrationBuilder
    0.61
     Gonna
    0.60
     gonna
    0.60
    jeka
    0.59
     happen
    0.59
     come
    0.58
    Act Density 0.077%

    No Known Activations