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

    Neuronpedia

    INDEX
    Explanations

    specific time schedules in text, typically denoted by 'E' followed by a time

    oai_token-act-pair · gpt-3.5-turbo

    specific group or event identifiers, likely associated with competition or awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Antar
    -0.88
     cher
    -0.86
     pudding
    -0.84
     Bam
    -0.80
     Tall
    -0.80
     Gin
    -0.78
     seiz
    -0.77
     bart
    -0.76
     ende
    -0.76
     gir
    -0.75
    POSITIVE LOGITS
    GC
    1.53
    RC
    1.53
    TA
    1.52
    CS
    1.51
    CA
    1.51
    SE
    1.50
    ND
    1.50
    IS
    1.49
    DA
    1.49
    RS
    1.49
    Act Density 0.109%

    No Known Activations