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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Mald
    -0.67
    phia
    -0.61
     Ports
    -0.61
     behavi
    -0.58
    ĺħ
    -0.55
     outweigh
    -0.54
    vana
    -0.53
     authority
    -0.52
     revolt
    -0.52
     Eid
    -0.52
    POSITIVE LOGITS
    58
    1.19
    06
    1.16
    59
    1.15
    04
    1.15
    53
    1.14
    54
    1.13
    02
    1.13
    57
    1.13
    05
    1.12
    07
    1.11
    Act Density 0.028%

    No Known Activations