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

    Neuronpedia

    INDEX
    Explanations

    mentions of having enough of something

    oai_token-act-pair · gpt-3.5-turbo

    references to identity and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARD
    -0.75
    Sport
    -0.71
    advertising
    -0.69
    MAP
    -0.69
    TYPE
    -0.67
    NESS
    -0.67
    Ĥİ
    -0.66
    HAEL
    -0.65
    Collect
    -0.65
    Strike
    -0.64
    POSITIVE LOGITS
     knack
    1.06
    been
    0.89
     chance
    0.89
     spare
    0.79
     flexibility
    0.79
     opportunity
    0.77
    ointed
    0.73
     penchant
    0.73
     cushion
    0.72
     tendency
    0.70
    Act Density 0.840%

    No Known Activations