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

    Neuronpedia

    INDEX
    Explanations

    words associated with different forms of "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilage
    -0.07
    ahren
    -0.07
    ooks
    -0.06
    iley
    -0.06
    ulers
    -0.06
    uner
    -0.06
    uling
    -0.06
    leigh
    -0.06
    ROWS
    -0.06
    .catalog
    -0.06
    POSITIVE LOGITS
    dera
    0.08
     Ludwig
    0.07
    eres
    0.07
    era
    0.07
    vard
    0.07
    iron
    0.06
    oren
    0.06
    оÑĢе
    0.06
     Loren
    0.06
    dfa
    0.06
    Act Density 0.001%

    No Known Activations