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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional advantages or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     līdz
    -0.34
     armées
    -0.34
     einheit
    -0.32
     rarement
    -0.31
     demais
    -0.29
     gouvernements
    -0.29
    ută
    -0.29
     industrielle
    -0.28
     nivelul
    -0.28
     auxquels
    -0.28
    POSITIVE LOGITS
    AndEndTag
    0.86
     Infórmanos
    0.84
     kasarigan
    0.79
    évaluateur
    0.78
     EconPapers
    0.76
     Taktlose
    0.73
    oredCriteria
    0.73
     zwiſchen
    0.71
    IntoConstraints
    0.69
    styleType
    0.69
    Act Density 0.215%

    No Known Activations