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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Since" followed by various markers indicating time or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     siguiente
    -0.16
    коÑĤ
    -0.15
    mens
    -0.15
     Leban
    -0.15
    ehler
    -0.15
    layan
    -0.14
    dam
    -0.14
    krv
    -0.14
    otlin
    -0.14
    mtree
    -0.14
    POSITIVE LOGITS
     since
    0.16
    arser
    0.15
    tant
    0.15
    Ùħا
    0.14
     lit
    0.14
    ammers
    0.13
    abez
    0.13
    Ŀ
    0.13
    ipple
    0.13
     lack
    0.13
    Act Density 0.039%

    No Known Activations