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

    Neuronpedia

    INDEX
    Explanations

    references to important principles or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bie
    -0.19
    ött
    -0.16
    ru
    -0.15
    ãĥĩãĥ«
    -0.15
    _relu
    -0.15
    ican
    -0.15
    emm
    -0.15
    ses
    -0.15
    ãĥĨãĥ«
    -0.14
    abilit
    -0.14
    POSITIVE LOGITS
    ist
    0.22
    ists
    0.22
    /basic
    0.21
    mente
    0.21
    istically
    0.19
     principals
    0.18
     flaw
    0.18
    /core
    0.18
    /original
    0.17
     principle
    0.17
    Act Density 0.033%

    No Known Activations