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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SSERT
    -0.17
    laz
    -0.15
    762
    -0.14
    lant
    -0.14
    rement
    -0.13
    à¥ģमत
    -0.13
    arkin
    -0.13
     one
    -0.13
    ë§IJ
    -0.13
    ongs
    -0.13
    POSITIVE LOGITS
     oneself
    0.21
     must
    0.20
     might
    0.19
    's
    0.19
     can
    0.19
     should
    0.19
    ’s
    0.18
     ought
    0.18
     shouldn
    0.18
     could
    0.18
    Act Density 0.048%

    No Known Activations