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

    Neuronpedia

    INDEX
    Explanations

    repetitive occurrences in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in a row" associated with numeric values representing consecutive events or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.80
    anamo
    -0.73
    irs
    -0.73
    onom
    -0.73
    Marginal
    -0.72
    ãĥ¤
    -0.70
     streng
    -0.70
    milo
    -0.64
    itars
    -0.63
    abilia
    -0.63
    POSITIVE LOGITS
    Fla
    0.78
     ..........
    0.75
     ago
    0.70
    VERT
    0.67
     before
    0.65
     since
    0.64
     begging
    0.64
    DOWN
    0.61
     -----
    0.60
    dy
    0.59
    Act Density 0.013%

    No Known Activations