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

    Neuronpedia

    INDEX
    Explanations

    occasions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to various events or occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hemat
    -0.76
    track
    -0.67
    utenberg
    -0.66
    cott
    -0.66
     rake
    -0.65
    gebra
    -0.62
    haul
    -0.62
    DS
    -0.61
     downhill
    -0.61
    overty
    -0.60
    POSITIVE LOGITS
     occasions
    0.93
     occasion
    0.88
    theless
    0.83
    enance
    0.75
    notes
    0.75
    issance
    0.74
    ional
    0.74
    forth
    0.74
    EMBER
    0.72
    cffffcc
    0.70
    Act Density 0.027%

    No Known Activations