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

    Neuronpedia

    INDEX
    Explanations

    expressions of determination and encouragement

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

    Infinitive marker "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    deciding to act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     traffico
    -0.64
    UnusedPrivate
    -0.60
     dibat
    -0.57
     numerus
    -0.57
    SharedCtor
    -0.56
     Taught
    -0.55
     ricordo
    -0.55
    יצוב
    -0.54
     Bioaccumulative
    -0.53
     لاح
    -0.53
    POSITIVE LOGITS
     proceed
    0.94
     risk
    0.92
     pursue
    0.88
     риск
    0.86
     PROCEED
    0.85
     risked
    0.83
     plunge
    0.81
     risking
    0.81
     embark
    0.81
     proceeding
    0.77
    Act Density 0.369%

    No Known Activations