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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences ending with special characters 'âĢĶ' and '•Ŀ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worms
    -0.82
    perate
    -0.77
     commun
    -0.73
    ordinate
    -0.72
    ieth
    -0.70
    interstitial
    -0.67
    ifi
    -0.67
    uminati
    -0.67
    userc
    -0.66
    reens
    -0.65
    POSITIVE LOGITS
    ————————
    1.66
    ————
    1.63
    ————————————————
    1.34
    ——
    0.95
    _-
    0.81
    âĢķ
    0.77
    particularly
    0.77
    ––
    0.76
    Maria
    0.74
     Kimber
    0.74
    Act Density 0.137%

    No Known Activations