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

    Neuronpedia

    INDEX
    Explanations

    numeric data related to experimental results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.74
    ExtendWith
    -0.68
    riwal
    -0.65
     linkovi
    -0.65
    ebaran
    -0.64
     EconPapers
    -0.64
    ArgsConstructor
    -0.62
    protoimpl
    -0.62
    aarrggbb
    -0.61
    fjspx
    -0.61
    POSITIVE LOGITS
     proto
    0.46
    ürnberg
    0.46
    ContentLoaded
    0.46
    kaner
    0.44
     Ali
    0.44
     desen
    0.44
    регистри
    0.43
    солю
    0.43
    wahati
    0.43
    dana
    0.42
    Act Density 0.011%

    No Known Activations