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

    Neuronpedia

    INDEX
    Explanations

    unicode characters related to specific software applications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character sequence 'âĢ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.77
     swept
    -0.72
    romy
    -0.70
     blond
    -0.70
     walking
    -0.68
     staggered
    -0.68
     Mayo
    -0.68
     dividing
    -0.67
     Plum
    -0.64
     Roma
    -0.64
    POSITIVE LOGITS
    £
    1.20
    ¬
    1.18
    ı
    1.17
    ¡
    1.13
    º
    1.11
    ¹
    1.10
    Ĵ
    1.09
    IJ
    1.06
    ij
    1.06
    ®
    1.06
    Act Density 0.229%

    No Known Activations