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

    Neuronpedia

    INDEX
    Explanations

    words related to perception or viewpoint

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    abouts
    -0.70
    bda
    -0.69
    externalActionCode
    -0.68
     confir
    -0.68
    isphere
    -0.62
    sonian
    -0.61
    intage
    -0.59
    osure
    -0.59
    scl
    -0.59
    oiler
    -0.58
    POSITIVE LOGITS
    phas
    1.03
    enance
    0.91
     themselves
    0.91
     himself
    0.82
     them
    0.82
     ourselves
    0.81
     him
    0.80
     myself
    0.77
     it
    0.76
     homosexuality
    0.72
    Act Density 0.245%

    No Known Activations