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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and urgency

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prompt responses or availability of comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.79
    ¥µ
    -0.66
    seless
    -0.65
    代
    -0.64
    illac
    -0.63
     NEVER
    -0.63
    ortment
    -0.63
    ħĭ
    -0.62
     ç¥ŀ
    -0.62
    èĢ
    -0.62
    POSITIVE LOGITS
     answered
    0.84
     responded
    0.80
     respond
    0.78
     reply
    0.69
     available
    0.68
     disclosed
    0.67
     satisf
    0.66
     replied
    0.66
    achable
    0.66
     reached
    0.65
    Act Density 0.032%

    No Known Activations