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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating waiting for something to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express waiting or anticipation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĦ
    -0.93
    ãĥ´
    -0.74
    rf
    -0.74
    ric
    -0.71
    uph
    -0.71
    minus
    -0.68
    ©¶æ¥µ
    -0.67
     sidel
    -0.67
    lower
    -0.66
    matter
    -0.65
    POSITIVE LOGITS
     reinforcements
    1.00
     arrival
    0.98
     confirmation
    0.92
     gratification
    0.90
     impatient
    0.89
     passage
    0.86
     someone
    0.82
     directions
    0.80
     sunrise
    0.80
     permission
    0.79
    Act Density 0.078%

    No Known Activations