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

    Neuronpedia

    INDEX
    Explanations

    time-related events or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.75
    bear
    -0.74
    ertain
    -0.69
    age
    -0.69
    ãĤ§
    -0.68
    augh
    -0.67
    zik
    -0.67
    stay
    -0.66
    ãĥ¼ãĥ
    -0.65
    ird
    -0.63
    POSITIVE LOGITS
    soever
    1.06
     they
    0.78
     confronted
    0.75
     comparing
    0.71
     compared
    0.70
     faced
    0.70
     someone
    0.69
     suddenly
    0.68
     hordes
    0.65
     she
    0.65
    Act Density 0.123%

    No Known Activations