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

    Neuronpedia

    INDEX
    Explanations

    discussions around political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contain
    -0.16
    .Italic
    -0.16
    NK
    -0.15
    Ngh
    -0.15
     consist
    -0.15
     expire
    -0.15
    obra
    -0.14
    olumn
    -0.14
    jourd
    -0.14
    beit
    -0.14
    POSITIVE LOGITS
     character
    0.36
    character
    0.32
     characterize
    0.30
     Character
    0.29
     accompany
    0.27
    Character
    0.27
     accompanies
    0.27
     karakter
    0.26
     CHARACTER
    0.25
     caratter
    0.25
    Act Density 0.251%

    No Known Activations