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

    Neuronpedia

    INDEX
    Explanations

    numeric expressions and indicators of measurement or scoring systems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -0.80
     themſelves
    -0.73
     himſelf
    -0.71
     Jefus
    -0.67
     Efq
    -0.67
     fometimes
    -0.66
     chofe
    -0.65
     pleaſure
    -0.63
    +:+
    -0.63
     Monfieur
    -0.63
    POSITIVE LOGITS
     оригіналу
    0.68
    ={`
    0.68
     AssemblyCulture
    0.68
    ArgsConstructor
    0.59
    InitStruct
    0.55
    ={`${
    0.55
     referenties
    0.53
     Доро
    0.52
     Zd
    0.52
    Jenn
    0.51
    Act Density 0.032%

    No Known Activations