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

    Neuronpedia

    INDEX
    Explanations

    detailed evaluations contrasting the positive and negative aspects of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.74
    elemField
    -0.63
     StringTokenizer
    -0.63
     $_"
    -0.63
     سكانية
    -0.62
     tartalomajánló
    -0.62
     authorship
    -0.62
    ########.
    -0.62
     myſelf
    -0.60
     majeure
    -0.60
    POSITIVE LOGITS
    AddTagHelper
    0.69
     CWE
    0.49
    GIVEREF
    0.49
    новништво
    0.47
    sieur
    0.46
    InjectAttribute
    0.45
     vezet
    0.44
    vänt
    0.44
     adegu
    0.43
    StoryboardSegue
    0.43
    Act Density 0.016%

    No Known Activations