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

    Neuronpedia

    INDEX
    Explanations

    references to specific paragraphs within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -0.66
     preſent
    -0.66
     ſtate
    -0.66
     ſtre
    -0.63
     raiſ
    -0.63
     ſta
    -0.62
    رشف
    -0.62
     propOrder
    -0.61
    ArgsConstructor
    -0.61
    makeConstraints
    -0.60
    POSITIVE LOGITS
    InitVars
    0.73
     attachment
    0.70
    strategic
    0.61
     attachments
    0.60
    END
    0.60
     MI
    0.59
     stratégique
    0.58
     Attachment
    0.58
     strategic
    0.57
    Strategic
    0.55
    Act Density 0.110%

    No Known Activations