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

    Neuronpedia

    INDEX
    Explanations

    mentions of knowledge and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uko
    -0.16
    еви
    -0.15
    ksen
    -0.15
    .ribbon
    -0.14
    ondheim
    -0.14
    rices
    -0.14
    elho
    -0.13
     kinetic
    -0.13
    istol
    -0.13
    sono
    -0.13
    POSITIVE LOGITS
    base
    0.43
     base
    0.37
    -base
    0.34
    bases
    0.33
     about
    0.31
    ably
    0.29
     bases
    0.29
    ability
    0.28
     gained
    0.28
     Base
    0.27
    Act Density 0.038%

    No Known Activations