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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs indicating statements or actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    odder
    -0.60
    iac
    -0.59
     Plaint
    -0.59
     Genius
    -0.57
     Cumber
    -0.57
    cial
    -0.56
     Dome
    -0.55
     Colonial
    -0.55
     Sussex
    -0.55
     Gad
    -0.54
    POSITIVE LOGITS
    'd
    0.91
     personally
    0.81
    've
    0.75
     regretted
    0.74
     encount
    0.74
    'll
    0.72
     own
    0.71
     intend
    0.69
     unres
    0.69
    stanbul
    0.67
    Act Density 21.100%

    No Known Activations