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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries about various topics and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANTE
    -0.17
     happen
    -0.16
    боÑĢ
    -0.16
    ante
    -0.15
    uke
    -0.14
    erset
    -0.14
    igham
    -0.14
    ument
    -0.14
    LATED
    -0.14
    onders
    -0.14
    POSITIVE LOGITS
     works
    0.19
     makes
    0.18
     Works
    0.17
     elements
    0.16
     really
    0.16
     matters
    0.16
     truly
    0.15
     realmente
    0.15
    works
    0.15
    æ§ĭ
    0.15
    Act Density 0.076%

    No Known Activations