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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     rightful
    -0.81
    sonian
    -0.81
    ersen
    -0.73
     dilig
    -0.72
    Versions
    -0.72
     adolesc
    -0.72
    Henry
    -0.70
    umenthal
    -0.69
    named
    -0.68
     appropriation
    -0.67
    POSITIVE LOGITS
    ooth
    1.16
    adesh
    0.93
    aby
    0.82
    inka
    0.81
    ucc
    0.81
    oths
    0.81
    oth
    0.78
    henko
    0.77
    azing
    0.77
    obo
    0.77
    Act Density 0.097%

    No Known Activations