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

    Neuronpedia

    INDEX
    Explanations

    negative contractions related to existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <?
    -0.66
     Spoon
    -0.66
     bib
    -0.64
    󠁴
    -0.64
     parap
    -0.63
     ſei
    -0.62
     Panorama
    -0.62
    alleye
    -0.61
     tif
    -0.61
     geſch
    -0.61
    POSITIVE LOGITS
     vôtre
    0.56
     quien
    0.52
     dieux
    0.51
     nôtre
    0.51
     deudas
    0.49
     isn
    0.48
     costes
    0.47
     antemano
    0.44
     jouet
    0.43
     précédents
    0.43
    Act Density 0.286%

    No Known Activations