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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "initial" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix 'ini.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deck
    -0.77
    phe
    -0.77
    spin
    -0.74
    lisher
    -0.73
    lehem
    -0.72
    taining
    -0.70
    theless
    -0.70
    lished
    -0.70
     mathemat
    -0.70
    phase
    -0.67
    POSITIVE LOGITS
    Äĩ
    1.09
    emi
    0.98
    otti
    0.97
    ya
    0.96
    zzle
    0.95
    ère
    0.95
    zzo
    0.91
    acs
    0.90
    ye
    0.89
    osa
    0.88
    Act Density 0.032%

    No Known Activations