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

    Neuronpedia

    INDEX
    Explanations

    sequences related to a specific word, "Ze"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the string "ze" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.84
    paced
    -0.81
    istrate
    -0.79
    acles
    -0.74
    ancial
    -0.70
    ridges
    -0.69
    rd
    -0.69
    osuke
    -0.67
    raising
    -0.67
    ials
    -0.67
    POSITIVE LOGITS
    lda
    1.31
    ppelin
    1.20
    zinski
    1.08
    cki
    0.96
    zza
    0.85
    ppy
    0.81
    ppel
    0.81
    ZZ
    0.79
    ppe
    0.78
    zz
    0.77
    Act Density 0.045%

    No Known Activations