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

    Neuronpedia

    INDEX
    Explanations

    mentions of joining or membership in different contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    fulness
    -0.76
     relate
    -0.72
     relates
    -0.72
     preceded
    -0.71
     namely
    -0.69
    ebted
    -0.68
    effic
    -0.68
    gradient
    -0.68
    erest
    -0.68
    houses
    -0.67
    POSITIVE LOGITS
     fray
    1.68
     ranks
    1.38
     chorus
    1.17
     bandwagon
    1.06
     fold
    0.98
     dots
    0.92
     conversation
    0.84
     queue
    0.84
     festivities
    0.83
     procession
    0.82
    Act Density 0.079%

    No Known Activations