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

    Neuronpedia

    INDEX
    Explanations

    the presence of temporal or spatial references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jsonwebtoken
    -0.67
     ddelweddau
    -0.64
     (\%)
    -0.63
    WebElementEntity
    -0.63
    θρώ
    -0.60
    apunov
    -0.59
    BASELINE
    -0.57
    ὖ
    -0.57
    ='';
    -0.57
    ":
    -0.57
    POSITIVE LOGITS
     which
    1.33
    which
    1.16
     whom
    0.97
     cuyo
    0.88
     WHICH
    0.87
     whose
    0.85
     cuya
    0.82
    Which
    0.81
     cui
    0.79
     cuyos
    0.79
    Act Density 0.784%

    No Known Activations