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

    Neuronpedia

    INDEX
    Explanations

    technical terms and identifiers used in programming or data models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.74
    ftagPool
    -0.54
     présentés
    -0.48
     and
    -0.47
     to
    -0.47
     ivelany
    -0.46
    DeleteBehavior
    -0.44
     pemimpin
    -0.43
    LOAT
    -0.42
     in
    -0.40
    POSITIVE LOGITS
    ⓧ
    0.96
     Reſ
    0.85
     Jefus
    0.85
     pleaſure
    0.84
     ſever
    0.82
     Diſ
    0.82
     Anſ
    0.81
     Inſ
    0.81
     themſelves
    0.81
    ſelves
    0.80
    Act Density 1.053%

    No Known Activations