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

    Neuronpedia

    INDEX
    Explanations

    references to a specific subject or topic within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✨:
    -0.81
     SPS
    -0.81
     himſelf
    -0.76
     craw
    -0.75
     GenerationType
    -0.73
     dandy
    -0.72
     faſt
    -0.72
     Efq
    -0.71
    ForRow
    -0.70
    😭😭
    -0.70
    POSITIVE LOGITS
     subject
    2.23
    subject
    2.05
     Subject
    2.05
     subjects
    1.97
    Subject
    1.93
     SUBJECT
    1.91
    SUBJECT
    1.83
     Subjects
    1.82
    subjects
    1.74
    Subjects
    1.72
    Act Density 0.067%

    No Known Activations