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

    Neuronpedia

    INDEX
    Explanations

    strings and their corresponding values in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.82
    SharedDtor
    -0.79
     Efq
    -0.78
     ſind
    -0.77
     Majefty
    -0.76
    addGap
    -0.75
     chofe
    -0.74
     AssemblyTitle
    -0.73
     himſelf
    -0.72
     itſelf
    -0.71
    POSITIVE LOGITS
     "
    0.78
    ("
    0.58
    ["
    0.56
    (@"
    0.56
     ("
    0.54
    "
    0.53
    (["
    0.52
     "(
    0.49
    +#+#
    0.48
     "$
    0.47
    Act Density 0.153%

    No Known Activations