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

    Neuronpedia

    INDEX
    Explanations

    words related to specific names or keywords in text

    oai_token-act-pair · gpt-3.5-turbo

    the name "Griffith" and its variations or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.68
    erers
    -0.67
     taped
    -0.65
     phone
    -0.63
    emet
    -0.63
     assisted
    -0.60
     focal
    -0.60
     pred
    -0.59
    opausal
    -0.58
     telephone
    -0.57
    POSITIVE LOGITS
    iffin
    1.18
    Gr
    1.06
    ands
    0.92
    ayson
    0.92
    rl
    0.87
    acies
    0.86
    ille
    0.85
    atche
    0.85
    unt
    0.83
    ains
    0.82
    Act Density 0.007%

    No Known Activations