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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating measurements or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hani
    -0.16
    otten
    -0.15
    son
    -0.15
    uet
    -0.15
    ees
    -0.14
    ast
    -0.14
    hd
    -0.14
    ortal
    -0.14
    iline
    -0.13
    ymax
    -0.13
    POSITIVE LOGITS
    isposable
    0.17
    NullOr
    0.16
    aeper
    0.16
    ities
    0.16
    ús
    0.15
    977
    0.15
     sav
    0.14
    amt
    0.14
    UIApplication
    0.14
    arat
    0.14
    Act Density 0.004%

    No Known Activations