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

    Neuronpedia

    INDEX
    Explanations

    references to specific materials or components commonly used in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibling
    -0.78
     Pradesh
    -0.78
    learn
    -0.69
     Lumpur
    -0.69
    ModLoader
    -0.66
    Ô
    -0.66
    cipled
    -0.64
    reditary
    -0.64
     opportun
    -0.63
    hower
    -0.63
    POSITIVE LOGITS
    ioxide
    0.82
     emb
    0.78
    oxide
    0.78
     sculptures
    0.76
     sculpture
    0.76
     sten
    0.74
    nels
    0.71
     strips
    0.70
     Sachs
    0.70
    icles
    0.69
    Act Density 0.106%

    No Known Activations