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

    Neuronpedia

    INDEX
    Explanations

    phrases related to chemical components or the effects of substances

    oai_token-act-pair · gpt-3.5-turbo

    key ingredients and components in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erved
    -0.73
    aris
    -0.69
    hran
    -0.66
    Characters
    -0.65
    htaking
    -0.63
    uss
    -0.63
    ariat
    -0.63
     ([
    -0.61
    rio
    -0.60
     Libraries
    -0.60
    POSITIVE LOGITS
     successor
    0.94
     precursor
    0.93
     predecessor
    0.90
     acronym
    0.83
     abbre
    0.78
     notoriously
    0.78
     constituent
    0.74
     holiest
    0.73
     perennial
    0.72
     competitor
    0.72
    Act Density 0.327%

    No Known Activations