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

    Neuronpedia

    INDEX
    Explanations

    occurrences of copyright symbols and closing parentheses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Shiloh
    -0.54
     proprement
    -0.52
    माण
    -0.47
    انجليز
    -0.46
     mahd
    -0.46
    Edited
    -0.42
    dorf
    -0.42
    保安
    -0.41
    ness
    -0.41
    nocache
    -0.40
    POSITIVE LOGITS
     kaynağından
    0.84
    Hentet
    0.81
    ThroughAttribute
    0.77
    ArgsConstructor
    0.77
     صوتيه
    0.77
    +:+
    0.75
     "..\..\..\
    0.75
    WEBPACK
    0.73
     CreateTagHelper
    0.73
    __":
    0.72
    Act Density 0.002%

    No Known Activations