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

    Neuronpedia

    INDEX
    Explanations

    links to forum threads and topics for online discussions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    leans
    -0.54
    estial
    -0.53
     Mandela
    -0.51
     Phelps
    -0.49
    SPONSORED
    -0.48
    skirts
    -0.46
    eton
    -0.45
    alties
    -0.45
     phased
    -0.43
     gin
    -0.43
    POSITIVE LOGITS
    forums
    0.57
    abuse
    0.54
    userc
    0.53
    bolt
    0.50
    bugs
    0.48
    ocker
    0.48
    ########
    0.48
    merce
    0.47
    ################
    0.46
    aimon
    0.46
    Act Density 7.825%

    No Known Activations