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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the current situation or status of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ceremon
    -0.74
     senses
    -0.69
     Yor
    -0.68
    ishers
    -0.67
     canoe
    -0.67
    isher
    -0.67
     whistle
    -0.66
    haw
    -0.66
     Gain
    -0.66
    agues
    -0.64
    POSITIVE LOGITS
    KER
    0.83
    GRE
    0.78
    Reviewer
    0.74
     Solitaire
    0.73
    Chicken
    0.70
    LG
    0.70
    SU
    0.69
    Ĥİ
    0.68
     actually
    0.68
    VALUE
    0.67
    Act Density 0.166%

    No Known Activations