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

    Neuronpedia

    INDEX
    Explanations

    statements expressing confusion or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alink
    -0.16
     znam
    -0.16
    åľ
    -0.15
    CAST
    -0.15
    åļ
    -0.15
    iske
    -0.15
    emean
    -0.14
    .ba
    -0.14
    contres
    -0.14
    .cg
    -0.14
    POSITIVE LOGITS
     mystery
    0.25
     baff
    0.25
     wonder
    0.25
     puzz
    0.23
     inexp
    0.21
    ocities
    0.20
     mysterious
    0.19
     puzzled
    0.19
     puzzles
    0.19
     Wonder
    0.19
    Act Density 0.175%

    No Known Activations