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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.95
    itaire
    -0.86
    Ļ½
    -0.82
    mud
    -0.82
    ounded
    -0.81
     Medina
    -0.81
    moil
    -0.81
     Trojan
    -0.79
    quartered
    -0.79
    asis
    -0.79
    POSITIVE LOGITS
    repeat
    0.91
     whatsoever
    0.90
    055
    0.83
     sir
    0.82
     except
    0.81
     Unloaded
    0.79
    é¾į
    0.77
    rists
    0.76
    ndra
    0.76
    ãĤ·ãĥ£
    0.75
    Act Density 3.047%

    No Known Activations