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

    Neuronpedia

    INDEX
    Explanations

    personal reflections and expressions of intent or thought

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

    Following verbs expressing intention, planning, or thought

    np_acts-logits-general · gemini-2.0-flash

    I will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arrivé
    -0.48
     TestBed
    -0.47
     gezicht
    -0.47
     welcomed
    -0.46
    enderror
    -0.44
     snoring
    -0.43
    <%=
    -0.42
    Scrolled
    -0.42
    ujete
    -0.41
     detalhe
    -0.41
    POSITIVE LOGITS
     will
    0.91
    shall
    0.79
     shall
    0.78
    will
    0.75
     Imma
    0.74
     Ill
    0.74
    Gonna
    0.72
     fhall
    0.72
     ill
    0.70
    我会
    0.68
    Act Density 0.313%

    No Known Activations