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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "since" indicating time references or temporal continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    коÑĤ
    -0.16
    ingt
    -0.15
    shed
    -0.14
    áºŃu
    -0.14
     siguiente
    -0.14
    krv
    -0.14
    Tween
    -0.14
    dam
    -0.14
    ÙĦÙĬÙĦ
    -0.14
    称
    -0.13
    POSITIVE LOGITS
     since
    0.16
    tant
    0.15
    IPS
    0.14
     lit
    0.14
     trouble
    0.14
    Ãł
    0.14
     troubles
    0.14
    xml
    0.13
    iren
    0.13
    ê»
    0.13
    Act Density 0.028%

    No Known Activations