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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases suggesting consideration or reflection on a topic or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest critical thinking or caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     maze
    -0.70
     Solitaire
    -0.65
     inability
    -0.64
     fog
    -0.64
     tang
    -0.63
     absentee
    -0.61
     fra
    -0.61
     fungi
    -0.61
     ozone
    -0.61
    ModLoader
    -0.59
    POSITIVE LOGITS
     someday
    0.88
     ASAP
    0.87
     emulate
    0.79
    arna
    0.78
    rosso
    0.73
    raise
    0.69
    boro
    0.69
    iquette
    0.68
     sometime
    0.68
    èĢħ
    0.67
    Act Density 0.219%

    No Known Activations