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

    Neuronpedia

    INDEX
    Explanations

    action words related to movement or interaction

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and adverbs indicating location or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemThumbnailImage
    -0.76
    JV
    -0.69
    hra
    -0.68
     limitation
    -0.67
     citation
    -0.65
    Import
    -0.65
    stellar
    -0.64
    ngth
    -0.64
    cano
    -0.64
    catentry
    -0.64
    POSITIVE LOGITS
     louder
    0.67
    orously
    0.67
     bab
    0.65
     passionately
    0.64
     outdoors
    0.64
     responsibly
    0.62
     bushes
    0.62
    aband
    0.61
    efully
    0.61
    aciously
    0.61
    Act Density 0.339%

    No Known Activations