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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to scientific processes or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geſch
    -0.74
    rogels
    -0.72
    yelidikan
    -0.68
    ähteet
    -0.67
    <bos>
    -0.65
    ੝
    -0.64
    󠁣
    -0.61
     Bewußt
    -0.60
    genodigd
    -0.60
     Menschheit
    -0.59
    POSITIVE LOGITS
     pro
    0.44
     base
    0.42
    دانشنامهٔ
    0.41
    DeleteBehavior
    0.41
    detectChanges
    0.41
     cas
    0.41
     super
    0.41
     prop
    0.40
     
    0.39
     can
    0.38
    Act Density 10.881%

    No Known Activations