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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to duration or the time required for actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ociated
    -0.79
    oeuv
    -0.78
    alde
    -0.76
    Associated
    -0.76
    vec
    -0.72
    ledged
    -0.70
    IED
    -0.70
    oided
    -0.68
    enemy
    -0.67
    arding
    -0.66
    POSITIVE LOGITS
     wrench
    0.73
     convincing
    0.70
     steps
    0.67
     adjustment
    0.67
     milliseconds
    0.67
     bite
    0.67
     precedence
    0.67
     toll
    0.67
     breaths
    0.64
     breat
    0.63
    Act Density 0.088%

    No Known Activations