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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "via."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nt
    -0.18
    ning
    -0.18
    woke
    -0.15
    sel
    -0.15
    ale
    -0.15
    GetProperty
    -0.14
    anie
    -0.14
    мена
    -0.14
    ped
    -0.14
    corr
    -0.14
    POSITIVE LOGITS
    ought
    0.20
    ogh
    0.19
    eniable
    0.17
    umbnail
    0.17
     versa
    0.17
    forth
    0.17
    664
    0.16
    857
    0.16
    149
    0.16
    agate
    0.16
    Act Density 0.018%

    No Known Activations