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

    Neuronpedia

    INDEX
    Explanations

    phrases related to moving or crossing physical spaces

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     wherea
    -0.84
     Shakspeare
    -0.80
     pamph
    -0.80
     encomp
    -0.77
     fortn
    -0.77
     unlaw
    -0.76
     resear
    -0.75
     contribut
    -0.75
     affor
    -0.74
     Khart
    -0.72
    POSITIVE LOGITS
     crossed
    1.03
     crossing
    0.99
     crosses
    0.89
    crossed
    0.88
     cross
    0.88
    crossing
    0.86
     crossings
    0.86
    Crossing
    0.80
     Crossing
    0.79
     crossover
    0.76
    Act Density 0.103%

    No Known Activations