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

    Neuronpedia

    INDEX
    Explanations

    time-related events or states

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs and phrases indicating completion or occurrence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ¸
    -0.66
     millenn
    -0.65
    anty
    -0.59
    guyen
    -0.57
    unker
    -0.57
    çīĪ
    -0.57
    oso
    -0.56
    eret
    -0.56
    paralle
    -0.56
     contingency
    -0.56
    POSITIVE LOGITS
    .[
    0.90
    .
    0.85
    .$
    0.81
    .;
    0.79
    !.
    0.78
    .","
    0.77
    ;
    0.76
    .—
    0.73
    .:
    0.72
    .(
    0.72
    Act Density 0.357%

    No Known Activations