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

    Neuronpedia

    INDEX
    Explanations

    future actions or commitments indicated by the word "will."

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

    "Will" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    will be followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     success
    -0.50
    success
    -0.44
     siker
    -0.42
     growth
    -0.41
     prediction
    -0.39
     successes
    -0.39
     successful
    -0.39
     موفقیت
    -0.39
     éxito
    -0.38
    hora
    -0.37
    POSITIVE LOGITS
    帖最后由
    0.66
    RTLR
    0.66
    __(/*!
    0.60
    SequentialGroup
    0.57
    0.56
     himſelf
    0.54
    PerformLayout
    0.54
    __":
    0.53
    .*")]
    0.52
     مشين
    0.51
    Act Density 0.206%

    No Known Activations