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

    Neuronpedia

    INDEX
    Explanations

    language indicating support, approval, or validation from others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terdam
    -0.18
    igham
    -0.17
    uddle
    -0.15
    cü
    -0.15
    _ISR
    -0.15
    _Enter
    -0.15
    suma
    -0.15
    anzeigen
    -0.15
    getOption
    -0.15
    zahl
    -0.15
    POSITIVE LOGITS
     support
    0.57
     backing
    0.42
    support
    0.38
     Support
    0.38
     cooperation
    0.37
     assistance
    0.35
     blessing
    0.35
    æĶ¯æĮģ
    0.34
    Support
    0.33
    upport
    0.31
    Act Density 0.152%

    No Known Activations