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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation methodologies and operational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antaranya
    -0.58
     keyCode
    -0.52
     jard
    -0.51
    VisualStudio
    -0.50
    円
    -0.49
    phrine
    -0.49
     serait
    -0.49
    draft
    -0.49
    Rifer
    -0.47
    ßer
    -0.47
    POSITIVE LOGITS
    LookAnd
    0.86
     obicei
    0.70
    ⓧ
    0.69
     تانيه
    0.68
     câte
    0.68
     onCancelled
    0.66
     pleaſure
    0.65
    gets
    0.65
     ddelweddau
    0.65
     majd
    0.64
    Act Density 1.272%

    No Known Activations