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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating summarization or clarification of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antlr
    -0.15
    clave
    -0.14
    orus
    -0.14
     mutlaka
    -0.14
    chyb
    -0.14
    ours
    -0.14
    aliz
    -0.14
    isma
    -0.14
     perhaps
    -0.14
    ense
    -0.14
    POSITIVE LOGITS
    å°±æĺ¯
    0.17
     saying
    0.16
     same
    0.15
    raison
    0.15
     identical
    0.15
    PerPixel
    0.15
    -minded
    0.15
     essentially
    0.15
    Same
    0.15
     glor
    0.14
    Act Density 0.046%

    No Known Activations