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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement, particularly going upwards and downwards

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vogli
    -0.51
    AfterEach
    -0.51
     pylab
    -0.51
     dimenti
    -0.51
    inguém
    -0.51
    XmlEnum
    -0.49
     shutil
    -0.49
     seaborn
    -0.47
    triangleq
    -0.47
     trovar
    -0.47
    POSITIVE LOGITS
     up
    1.04
    up
    0.95
     Up
    0.95
     UP
    0.93
    Up
    0.90
    UP
    0.84
    ups
    0.75
     ups
    0.74
    upy
    0.67
    アップ
    0.67
    Act Density 0.127%

    No Known Activations