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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating action or accomplishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooting
    -0.74
    eka
    -0.73
    ritical
    -0.73
    shared
    -0.70
    peria
    -0.69
    oot
    -0.68
    aun
    -0.68
    ¿½
    -0.67
    dt
    -0.67
    oda
    -0.67
    POSITIVE LOGITS
     awfully
    0.89
     lately
    0.80
     dangerously
    0.78
     alright
    0.77
     ducks
    0.70
     steadily
    0.68
     fools
    0.67
     trouble
    0.67
     alot
    0.67
     pretty
    0.67
    Act Density 0.396%

    No Known Activations