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

    Neuronpedia

    INDEX
    Explanations

    comparisons and evaluations of value or superiority in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NotImplemented
    -0.16
    èn
    -0.15
    .Abstractions
    -0.15
     Vit
    -0.15
     overd
    -0.14
     customary
    -0.14
    vit
    -0.14
    iÄĩ
    -0.14
    .enumer
    -0.14
    elsey
    -0.14
    POSITIVE LOGITS
     contrast
    0.27
     favor
    0.25
     favour
    0.25
     Favor
    0.24
    contrast
    0.24
     Contrast
    0.23
    favor
    0.22
     contrasts
    0.21
     fav
    0.21
     advantage
    0.19
    Act Density 0.028%

    No Known Activations