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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or quantities related to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yang
    -0.16
    yor
    -0.15
     Bram
    -0.15
    ytt
    -0.14
    ty
    -0.14
    undler
    -0.14
     interiors
    -0.14
    742
    -0.14
     ben
    -0.13
    rary
    -0.13
    POSITIVE LOGITS
    еÑĢина
    0.15
    Č↵
    0.15
     Sloan
    0.14
    Inspector
    0.14
    pheric
    0.14
     Inspector
    0.14
    sey
    0.14
    ylon
    0.13
     Domino
    0.13
     unsafe
    0.13
    Act Density 0.230%

    No Known Activations