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

    Neuronpedia

    INDEX
    Explanations

    adverbs that end in -ly

    oai_token-act-pair · gpt-3.5-turbo

    adverbs, particularly those describing manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilater
    -0.87
     GOODMAN
    -0.80
    afety
    -0.80
     Extrem
    -0.76
     Julio
    -0.75
    eport
    -0.69
    icans
    -0.68
    anian
    -0.67
    ilion
    -0.67
    esson
    -0.63
    POSITIVE LOGITS
    rics
    0.87
    ffe
    0.83
     adv
    0.83
    tics
    0.80
    present
    0.80
    clad
    0.78
    zed
    0.77
    puff
    0.74
     dispose
    0.74
    gged
    0.73
    Act Density 0.039%

    No Known Activations