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

    Neuronpedia

    INDEX
    Explanations

    references to collective entities, such as sectors, nations, or the whole

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.38
    rets
    -0.34
    anwhile
    -0.33
    hester
    -0.31
     DRAG
    -0.31
     newsletters
    -0.30
    stories
    -0.30
     briefs
    -0.29
    cakes
    -0.29
    ANS
    -0.29
    POSITIVE LOGITS
    heartedly
    0.47
    hearted
    0.42
     extent
    0.35
     spectrum
    0.35
     hemisphere
    0.33
     width
    0.32
     breadth
    0.32
    ignment
    0.31
    owment
    0.31
     gam
    0.31
    Act Density 7.194%

    No Known Activations