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

    Neuronpedia

    INDEX
    Explanations

    words that contain the letters 'ed' consecutively

    oai_token-act-pair · gpt-4-turbo

    phrases containing the word "ed" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "editing" or "edited" forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Story
    -0.70
    ATCH
    -0.65
     Bayer
    -0.64
     Kiss
    -0.64
     Nun
    -0.63
    ãĥ¯ãĥ³
    -0.63
    LLOW
    -0.63
    ATT
    -0.61
     Republic
    -0.60
     Hunters
    -0.59
    POSITIVE LOGITS
    ifice
    1.20
    nesday
    1.00
    ict
    1.00
    ging
    0.99
    monton
    0.97
    icy
    0.93
    gew
    0.92
    uce
    0.92
    ocument
    0.92
    dy
    0.91
    Act Density 0.005%

    No Known Activations