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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions highlighting oppositional concepts or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nito
    -0.45
     exten
    -0.38
    endix
    -0.38
    blatt
    -0.38
    )&&
    -0.37
     přek
    -0.37
     Customs
    -0.37
    entas
    -0.36
    estre
    -0.36
     cie
    -0.36
    POSITIVE LOGITS
    GEBURTSDATUM
    0.91
     WHETHER
    0.89
     whether
    0.87
     SwitchCompat
    0.84
     verschil
    0.81
    protoimpl
    0.80
     versus
    0.80
     snippetHide
    0.77
    versus
    0.74
    MigrationBuilder
    0.74
    Act Density 0.877%

    No Known Activations