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

    Neuronpedia

    INDEX
    Explanations

    specialized technical terms related to machine learning and artificial intelligence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     -
    -0.50
    .
    -0.49
    ↵↵
    -0.46
    +',
    -0.46
    ',
    -0.44
     |
    -0.43
    ,
    -0.42
     +
    -0.41
     when
    -0.41
    pro
    -0.41
    POSITIVE LOGITS
     lenker
    0.91
     Efq
    0.91
    AddTagHelper
    0.83
    AndEndTag
    0.82
     chofe
    0.82
     houſe
    0.82
     purpoſe
    0.81
     pleaſure
    0.81
    EndInit
    0.80
    migrationBuilder
    0.80
    Act Density 0.006%

    No Known Activations