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

    Neuronpedia

    INDEX
    Explanations

    terms related to axes and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rait
    -0.16
    chal
    -0.16
    icas
    -0.16
    jective
    -0.16
    ween
    -0.15
    fik
    -0.15
    fic
    -0.15
    erset
    -0.15
    acock
    -0.15
    ancock
    -0.15
    POSITIVE LOGITS
    ially
    0.23
    illary
    0.23
    ioms
    0.22
    ial
    0.20
    cess
    0.20
    istence
    0.19
    ymmetric
    0.19
    iali
    0.18
    lsx
    0.17
    ialis
    0.17
    Act Density 0.019%

    No Known Activations