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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions conveying personal thoughts and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.72
    ьаж
    -0.66
     kasarigan
    -0.65
     Tole
    -0.64
    AsUp
    -0.64
     Boletín
    -0.63
    -------------</
    -0.61
     Marbella
    -0.61
    destroyAll
    -0.60
    Clik
    -0.60
    POSITIVE LOGITS
     recently
    0.57
     wondering
    0.55
     I
    0.52
     figure
    0.51
     
    0.48
    غال
    0.47
    FIGURE
    0.46
     wondered
    0.46
     thought
    0.44
    vious
    0.44
    Act Density 0.216%

    No Known Activations