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

    Neuronpedia

    INDEX
    Explanations

    organizations and events mentioned in news articles or press releases

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    sup
    -0.61
     Frozen
    -0.60
    arde
    -0.60
    tons
    -0.59
     Cyborg
    -0.58
    icent
    -0.57
     Schr
    -0.55
     cit
    -0.55
     Creed
    -0.55
    ses
    -0.55
    POSITIVE LOGITS
    SHARE
    0.72
    Politics
    0.71
    DEN
    0.70
    Econom
    0.70
    jer
    0.69
    MON
    0.67
    NA
    0.65
    ccording
    0.65
    Feb
    0.64
    BBC
    0.64
    Act Density 0.080%

    No Known Activations