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

    Neuronpedia

    INDEX
    Explanations

    phrases related to crossing boundaries or lines

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    PDATE
    -0.52
    spot
    -0.50
     expended
    -0.50
    LESS
    -0.49
    ufact
    -0.47
     shaping
    -0.46
     tuning
    -0.45
     rebuilt
    -0.43
    EMP
    -0.43
     endors
    -0.43
    POSITIVE LOGITS
     borders
    0.70
     boundaries
    0.69
     bounds
    0.63
    rome
    0.60
    border
    0.58
    danger
    0.56
    Border
    0.56
    agall
    0.56
     continents
    0.53
     fray
    0.52
    Act Density 13.182%

    No Known Activations