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

    Neuronpedia

    INDEX
    Explanations

    issues, criticisms, and objections

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    catentry
    -0.76
    ggles
    -0.70
     skyrocket
    -0.66
    ctica
    -0.63
    aults
    -0.61
    byter
    -0.61
    chet
    -0.60
    clerosis
    -0.59
    umatic
    -0.59
    rencies
    -0.58
    POSITIVE LOGITS
     whatsoever
    0.76
     attaching
    0.74
    Nusra
    0.66
     letting
    0.65
     admitting
    0.65
    lihood
    0.63
     having
    0.61
     saying
    0.61
    doing
    0.61
    acity
    0.60
    Act Density 0.122%

    No Known Activations