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

    Neuronpedia

    INDEX
    Explanations

    words related to capability or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setValue
    -0.16
    /antlr
    -0.15
    rrha
    -0.15
    SHORT
    -0.15
    stick
    -0.15
    ynet
    -0.15
    cts
    -0.14
    etak
    -0.14
    ennen
    -0.14
    abbo
    -0.14
    POSITIVE LOGITS
    ITH
    0.16
     larg
    0.15
    eso
    0.15
    大人
    0.14
    ith
    0.14
    ibo
    0.14
    ê
    0.14
     pro
    0.14
     Dund
    0.14
    ndo
    0.14
    Act Density 0.001%

    No Known Activations