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

    Neuronpedia

    INDEX
    Explanations

    terms related to metrics or evaluation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ones
    -0.07
    obel
    -0.06
    misc
    -0.06
    569
    -0.06
    ench
    -0.06
    ãĤĥ
    -0.06
    strom
    -0.06
    _hint
    -0.06
    ivel
    -0.06
    Misc
    -0.06
    POSITIVE LOGITS
    /frontend
    0.07
     antlr
    0.07
     [[]
    0.07
    odash
    0.07
    isify
    0.07
    ixo
    0.07
    unday
    0.07
    gii
    0.06
     RAT
    0.06
    cko
    0.06
    Act Density 0.029%

    No Known Activations