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

    Neuronpedia

    INDEX
    Explanations

    words related to political events or social issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     "$:/
    -0.70
     affiliation
    -0.63
     connection
    -0.62
     radiant
    -0.61
    OTO
    -0.60
     overturn
    -0.60
     FANTASY
    -0.59
     Â
    -0.59
     neutral
    -0.58
     appe
    -0.58
    POSITIVE LOGITS
    ums
    4.81
    um
    2.21
    UM
    1.90
    ummies
    1.36
    ummy
    1.31
    umn
    1.31
    umps
    1.22
    ummer
    1.22
    umb
    1.15
    umm
    1.15
    Act Density 0.008%

    No Known Activations