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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to measurements and analysis in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.73
     NSCoder
    -0.71
    msgTypes
    -0.71
    !*\
    -0.71
    AnchorStyles
    -0.70
     Roskov
    -0.65
    aarrggbb
    -0.64
    routeProvider
    -0.63
    IsMutable
    -0.62
    contentLoaded
    -0.61
    POSITIVE LOGITS
     compreensão
    0.49
     compréhen
    0.48
     antaranya
    0.48
     uds
    0.46
     identificação
    0.46
    WaitGroup
    0.46
     compren
    0.43
     teritor
    0.43
     vanske
    0.43
    Cred
    0.42
    Act Density 0.508%

    No Known Activations