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

    Neuronpedia

    INDEX
    Explanations

    sequences of words that describe steps, instructions, or rules

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "as follows."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olla
    -0.80
    oll
    -0.78
    orc
    -0.77
    ricular
    -0.70
    owered
    -0.69
    oard
    -0.69
     earthqu
    -0.66
    vere
    -0.66
    olin
    -0.65
    anyon
    -0.64
    POSITIVE LOGITS
     follows
    1.16
    bourg
    0.86
    follow
    0.85
     followed
    0.82
     follow
    0.81
     Follow
    0.79
    ĸļ
    0.78
     pursu
    0.72
     susp
    0.71
    ¿½
    0.66
    Act Density 0.006%

    No Known Activations