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

    Neuronpedia

    INDEX
    Explanations

    instances of prepositions in various contexts

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

    no followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorisations
    -0.65
    ########.
    -0.60
    URLException
    -0.59
    colhead
    -0.57
    出版年
    -0.56
    Betsy
    -0.55
     informée
    -0.55
    AutoScale
    -0.54
    مصادر
    -0.54
    CrossRef
    -0.54
    POSITIVE LOGITS
     in
    1.02
     nello
    0.80
     In
    0.79
     on
    0.79
     nella
    0.78
     στην
    0.76
     στον
    0.74
     στη
    0.74
     at
    0.69
    ใน
    0.69
    Act Density 0.001%

    No Known Activations