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

    Neuronpedia

    INDEX
    Explanations

    statements and terms related to preferences and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rem
    -0.56
     viață
    -0.46
    地道
    -0.44
    notes
    -0.44
     timmar
    -0.44
     asupra
    -0.44
    vides
    -0.43
     pełni
    -0.43
     Had
    -0.43
     bestand
    -0.42
    POSITIVE LOGITS
    StructEnd
    1.08
    InputBorder
    0.98
     overlap
    0.95
     AssemblyCulture
    0.93
     Anſ
    0.90
    mybatisplus
    0.88
     Houſe
    0.88
    preference
    0.85
    preferences
    0.85
    IsContent
    0.84
    Act Density 0.086%

    No Known Activations