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

    Neuronpedia

    INDEX
    Explanations

    verbs relating to actions or initiatives being taken

    oai_token-act-pair · gpt-3.5-turbo

    actions related to initiating, preparing, or advocating for various processes or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sac
    -0.72
    she
    -0.66
    worthiness
    -0.66
    agging
    -0.66
    wrong
    -0.65
     preceding
    -0.65
    abiding
    -0.65
    ritical
    -0.63
     occurring
    -0.63
    xe
    -0.63
    POSITIVE LOGITS
     furiously
    0.78
     ducks
    0.73
     preparations
    0.71
     cautiously
    0.69
     anew
    0.67
     efforts
    0.65
     contingency
    0.65
     volunteers
    0.65
     frantically
    0.65
     developments
    0.63
    Act Density 0.356%

    No Known Activations