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

    Neuronpedia

    INDEX
    Explanations

    names and renaming actions within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of naming and renaming in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azaki
    -0.73
     tempted
    -0.73
    isman
    -0.72
    istries
    -0.69
    ivariate
    -0.68
    blogs
    -0.68
     touched
    -0.67
    Constructed
    -0.67
    achev
    -0.66
     reached
    -0.65
    POSITIVE LOGITS
     ç¥ŀ
    0.86
     '
    0.77
     ''
    0.77
     Kw
    0.76
     Schw
    0.75
     Eff
    0.74
     Ago
    0.74
     Theodore
    0.72
     "
    0.72
     \"
    0.72
    Act Density 0.178%

    No Known Activations