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

    Neuronpedia

    INDEX
    Explanations

    economic and financial terms or indicators

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    YD
    -0.77
    say
    -0.77
     Vaugh
    -0.75
    OTUS
    -0.75
    together
    -0.73
    ITH
    -0.73
    employed
    -0.71
    inet
    -0.71
    urnal
    -0.70
    yre
    -0.70
    POSITIVE LOGITS
    wards
    0.83
     persecut
    0.76
    ctors
    0.76
     agon
    0.74
    udeau
    0.71
     beaut
    0.69
    oard
    0.67
     manner
    0.67
     imm
    0.67
     judgement
    0.67
    Act Density 8.086%

    No Known Activations