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

    Neuronpedia

    INDEX
    Explanations

    references to blog posts and their content

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    enderror
    -0.62
    DebuggerNonUser
    -0.60
    }$}
    -0.59
    TagHelpers
    -0.58
    $}}
    -0.58
    ører
    -0.57
    WireFormatLite
    -0.57
    ++]=
    -0.56
    newtheorem
    -0.55
    )$}
    -0.55
    POSITIVE LOGITS
    Datuak
    0.57
     phal
    0.57
     jadx
    0.56
     оригіналу
    0.55
    ensement
    0.54
    rawDesc
    0.54
    Identyfik
    0.53
     bParam
    0.52
    élien
    0.52
     ferru
    0.51
    Act Density 0.032%

    No Known Activations