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

    Neuronpedia

    INDEX
    Explanations

    phrases related to angles or directions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.56
    ⓧ
    -0.96
    /**
    -0.79
    /*
    -0.71
    <?
    -0.62
     ren
    -0.59
    
    -0.59
     put
    -0.59
    Élet
    -0.58
     Kar
    -0.57
    POSITIVE LOGITS
     angle
    1.46
     Angle
    1.39
     angles
    1.38
    Angle
    1.22
     Minang
    1.22
    angle
    1.19
     ANGLE
    1.16
     meis
    1.14
     Angles
    1.13
     kram
    1.12
    Act Density 0.313%

    No Known Activations