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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transitions or progressions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ghai
    -0.70
     timetable
    -0.69
    rike
    -0.67
    zai
    -0.63
    idas
    -0.63
    gow
    -0.63
    cpu
    -0.62
    cu
    -0.61
    yip
    -0.61
     Compare
    -0.60
    POSITIVE LOGITS
     adulthood
    1.22
     unch
    1.04
     obscurity
    0.98
     adolescence
    0.86
     realms
    0.82
    clusion
    0.82
     darkness
    0.77
     ob
    0.75
     homelessness
    0.74
     territory
    0.72
    Act Density 0.106%

    No Known Activations