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

    Neuronpedia

    INDEX
    Explanations

    comparisons or likenings between various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    oÄŁ
    -0.72
    Assembly
    -0.66
     oats
    -0.64
    ailability
    -0.61
    ktop
    -0.60
    IDE
    -0.60
    absor
    -0.59
     assembly
    -0.59
    hoff
    -0.57
    lite
    -0.56
    POSITIVE LOGITS
    isons
    0.82
    xual
    0.82
     favorably
    0.70
     sidx
    0.69
    ivil
    0.69
    lihood
    0.67
    SHIP
    0.67
    PsyNetMessage
    0.66
     homosexuality
    0.65
     lik
    0.64
    Act Density 8.675%

    No Known Activations