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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns related to years or figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to monetary values and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     polyg
    -0.67
     Ly
    -0.67
     isot
    -0.67
     Lit
    -0.66
     rice
    -0.66
     Atlas
    -0.63
     roll
    -0.63
    aly
    -0.63
     lett
    -0.63
     rele
    -0.63
    POSITIVE LOGITS
    77
    2.71
    79
    2.67
    78
    2.60
    76
    2.51
    81
    2.16
    82
    2.13
    83
    2.03
    73
    2.02
    74
    2.02
    71
    1.90
    Act Density 0.063%

    No Known Activations