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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing various personal attributes or qualities

    oai_token-act-pair · gpt-3.5-turbo

    nouns or phrases describing significant attributes or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inel
    -0.81
    adequ
    -0.77
    agents
    -0.75
    iterator
    -0.73
    states
    -0.72
    Aren
    -0.68
    operator
    -0.67
    Anonymous
    -0.66
    verage
    -0.66
    Americans
    -0.65
    POSITIVE LOGITS
     knack
    1.51
     penchant
    1.33
     reputation
    1.12
     beard
    1.09
     flair
    1.08
     girlfriend
    1.04
     mustache
    1.04
     habit
    1.02
     cameo
    1.02
     tendency
    1.00
    Act Density 0.145%

    No Known Activations