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

    Neuronpedia

    INDEX
    Explanations

    references to time periods and chronological events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eenth
    -0.19
    andin
    -0.17
    åįģåħ«
    -0.17
     TEN
    -0.17
     Ten
    -0.17
    _ten
    -0.17
    18
    -0.16
     Fif
    -0.16
    над
    -0.16
    åįģä¸Ģ
    -0.16
    POSITIVE LOGITS
     half
    0.43
    50
    0.36
    half
    0.34
     HALF
    0.33
     decades
    0.33
    40
    0.33
     Half
    0.33
    60
    0.32
    70
    0.31
     quarter
    0.31
    Act Density 0.067%

    No Known Activations