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

    Neuronpedia

    INDEX
    Explanations

    instructions or actions related to examining, reviewing, or analyzing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    look at / examining / review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zijne
    -0.38
     urbanas
    -0.37
     Annahme
    -0.37
    feitura
    -0.36
     Partager
    -0.35
     otomatig
    -0.34
     beginnetje
    -0.33
    PreferredItem
    -0.32
    isateur
    -0.32
    ndorf
    -0.32
    POSITIVE LOGITS
     regarder
    0.68
    look
    0.67
     glance
    0.66
    viewing
    0.66
     melihat
    0.63
     perusal
    0.63
     miró
    0.63
     viewing
    0.63
    看了
    0.62
    Look
    0.61
    Act Density 0.427%

    No Known Activations