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

    Neuronpedia

    INDEX
    Explanations

    mathematical definitions and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gos
    -0.17
    bud
    -0.15
    tein
    -0.15
    alach
    -0.15
    ãĥĥ
    -0.15
    aktu
    -0.14
    quia
    -0.14
     Bard
    -0.14
    alin
    -0.14
    ocale
    -0.13
    POSITIVE LOGITS
    label
    0.31
     label
    0.24
     labeled
    0.23
     Labels
    0.23
     labels
    0.21
     LABEL
    0.21
     Label
    0.20
     labelled
    0.20
    .label
    0.19
    LABEL
    0.19
    Act Density 0.043%

    No Known Activations