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

    Neuronpedia

    INDEX
    Explanations

    references to authorship, decisions, and potential actions or lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seem
    -0.22
     seems
    -0.22
    好åĥı
    -0.20
     Seems
    -0.18
    .say
    -0.17
     seemed
    -0.16
     seeming
    -0.16
    says
    -0.16
     parece
    -0.16
     Says
    -0.15
    POSITIVE LOGITS
     meant
    0.27
     intended
    0.20
     forgot
    0.18
     somehow
    0.17
     either
    0.16
     algún
    0.15
     means
    0.15
     somewhere
    0.15
    ож
    0.15
    ÑĨо
    0.15
    Act Density 0.246%

    No Known Activations