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

    Neuronpedia

    INDEX
    Explanations

    negative statements about capability or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ss
    -0.18
    ifes
    -0.18
     Aires
    -0.16
     indeed
    -0.15
     zwar
    -0.15
    iana
    -0.14
    اÙĪÙĦ
    -0.14
     totiž
    -0.13
    аÑĢÑĤ
    -0.13
     +↵↵
    -0.13
    POSITIVE LOGITS
     necessarily
    0.21
    åľŃ
    0.17
     actual
    0.17
     Helm
    0.16
     actually
    0.15
    ld
    0.14
     è³
    0.14
    Disposed
    0.14
    åį´
    0.14
    .eql
    0.14
    Act Density 0.234%

    No Known Activations