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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that express complexity and nuance in human experiences or situations

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

    "a" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    a lot of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.70
     évent
    -0.61
     betweenstory
    -0.60
     Effort
    -0.56
    /#{
    -0.56
     fiind
    -0.55
     esfuerzo
    -0.55
    effort
    -0.55
     abbraccio
    -0.53
     effort
    -0.52
    POSITIVE LOGITS
     tendency
    1.02
     penchant
    0.83
     estekak
    0.83
     knack
    0.82
    AndEndTag
    0.77
     vested
    0.72
     problem
    0.72
     оригіналу
    0.69
     reputation
    0.68
     محفوظة
    0.67
    Act Density 0.184%

    No Known Activations