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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the pattern "one-[number]" where number can be any digit

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing "one-off" events or single instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.72
     Hoo
    -0.69
     Borders
    -0.64
    âĶģ
    -0.62
     Stra
    -0.62
    emetery
    -0.61
    âĸ¬âĸ¬
    -0.60
    ITED
    -0.60
     laun
    -0.58
     SIG
    -0.58
    POSITIVE LOGITS
    sided
    1.38
    dimensional
    1.29
    legged
    1.19
    year
    1.18
    piece
    1.17
    bedroom
    1.14
    handed
    1.13
    minute
    1.13
    eyed
    1.13
    day
    1.07
    Act Density 0.038%

    No Known Activations