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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of solutions or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     change
    -0.52
    oredCriteria
    -0.52
     Change
    -0.46
     CHANGE
    -0.45
    DeleteBehavior
    -0.43
     only
    -0.43
     informée
    -0.43
    Change
    -0.41
    tagext
    -0.41
     EconPapers
    -0.40
    POSITIVE LOGITS
     ways
    0.91
     esistono
    0.89
     snippetHide
    0.79
     alternatives
    0.77
     Anſ
    0.75
    DOCTYPE
    0.74
    ⋙
    0.74
     esiste
    0.72
     findes
    0.72
     BoxDecoration
    0.72
    Act Density 0.183%

    No Known Activations