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

    Neuronpedia

    INDEX
    Explanations

    references to text markdown (MD) syntax

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.73
    nel
    -0.73
    stall
    -0.72
    acters
    -0.70
    lio
    -0.70
    asonable
    -0.69
    istic
    -0.68
    cluded
    -0.68
     LAPD
    -0.67
    =-=-=-=-=-=-=-=-
    -0.66
    POSITIVE LOGITS
    iamond
    1.06
    ART
    0.87
    ouble
    0.86
    IVER
    0.83
    Gs
    0.82
    ULT
    0.81
    ARS
    0.81
    aughter
    0.80
    AY
    0.79
    HC
    0.79
    Act Density 0.015%

    No Known Activations