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

    Neuronpedia

    INDEX
    Explanations

    instances of particular occasions or events mentioned in a context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "occasion" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.72
    hemat
    -0.71
    haar
    -0.67
    track
    -0.64
    gebra
    -0.64
    bern
    -0.63
    thereum
    -0.63
    haul
    -0.62
    agra
    -0.62
    cott
    -0.62
    POSITIVE LOGITS
     occasions
    0.94
    theless
    0.89
     occasion
    0.87
    ional
    0.78
    orial
    0.77
    forth
    0.74
    EMBER
    0.72
    aneous
    0.72
    icular
    0.71
    enance
    0.71
    Act Density 0.035%

    No Known Activations