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

    Neuronpedia

    INDEX
    Explanations

    phrases that include different forms of the word "up" and related directional terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Abonnez
    -0.76
     Hopf
    -0.64
     páss
    -0.64
     SSC
    -0.64
     gering
    -0.63
     Inscrivez
    -0.63
     Poisson
    -0.62
     MPEG
    -0.60
    âng
    -0.60
     '{@
    -0.59
    POSITIVE LOGITS
     الحره
    0.79
     referenties
    0.77
    AndEndTag
    0.76
    IUrlHelper
    0.71
    thâu
    0.70
    évaluateur
    0.68
     estekak
    0.66
    DialogContent
    0.65
    Diweddarwch
    0.61
    ponses
    0.61
    Act Density 0.213%

    No Known Activations