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

    Neuronpedia

    INDEX
    Explanations

    referential pronouns indicating causality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewe
    -0.19
    hed
    -0.16
    eya
    -0.15
    utenberg
    -0.15
    tü
    -0.15
    äm
    -0.15
    ilde
    -0.15
    onaut
    -0.14
    ungeons
    -0.14
    elon
    -0.14
    POSITIVE LOGITS
    ance
    0.15
     ancor
    0.14
    IgnoreCase
    0.14
    /preferences
    0.14
     tane
    0.14
    IRROR
    0.14
    REDENTIAL
    0.14
    Ĥ¬
    0.13
     Ci
    0.13
    ious
    0.13
    Act Density 0.000%

    No Known Activations