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

    Neuronpedia

    INDEX
    Explanations

    numbered subsections or headers

    oai_token-act-pair · gpt-3.5-turbo

    numeric identifiers or quantities, likely related to ranking or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gart
    -0.76
     tremend
    -0.71
    ierrez
    -0.70
    gone
    -0.65
    ause
    -0.65
    spread
    -0.65
    anamo
    -0.64
    iques
    -0.61
    assetsadobe
    -0.61
     avail
    -0.60
    POSITIVE LOGITS
    66
    0.96
    37
    0.92
    rd
    0.89
     Reasons
    0.89
    491
    0.86
    87
    0.84
    94
    0.83
    71
    0.83
    76
    0.82
    77
    0.81
    Act Density 0.039%

    No Known Activations