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

    Neuronpedia

    INDEX
    Explanations

    professional titles and roles related to various fields

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    different
    -0.69
     blister
    -0.64
    zb
    -0.63
    plet
    -0.62
    uder
    -0.60
    ividual
    -0.60
    ether
    -0.60
    ayers
    -0.59
    crew
    -0.59
    ecycle
    -0.58
    POSITIVE LOGITS
     extraord
    1.70
     emer
    0.93
    ially
    0.86
     laureate
    0.81
    itatively
    0.78
    uably
    0.77
    esses
    0.75
    Joined
    0.74
     Emer
    0.70
     darling
    0.69
    Act Density 0.181%

    No Known Activations