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

    Neuronpedia

    INDEX
    Explanations

    terms related to definitions and explaining concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eros
    -0.19
    ero
    -0.17
    da
    -0.17
    or
    -0.17
    ylon
    -0.16
    ice
    -0.15
    /down
    -0.15
    od
    -0.15
    odge
    -0.15
    at
    -0.15
    POSITIVE LOGITS
    undef
    0.18
    eated
    0.17
     undef
    0.17
    hower
    0.17
    nock
    0.16
    .Def
    0.16
    erialized
    0.15
    hin
    0.15
    Wunused
    0.15
    /Instruction
    0.15
    Act Density 0.047%

    No Known Activations