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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical values in sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     disgra
    -0.81
     pessi
    -0.77
     unil
    -0.76
     tph
    -0.75
     aton
    -0.74
     pamph
    -0.74
     vagab
    -0.73
     emphat
    -0.73
     racon
    -0.72
     contex
    -0.71
    POSITIVE LOGITS
     percent
    0.61
    percent
    0.56
     față
    0.52
     chance
    0.52
     reduction
    0.51
     percentage
    0.51
    /%
    0.50
     toată
    0.50
    setAlignment
    0.50
    }%
    0.49
    Act Density 0.235%

    No Known Activations