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

    Neuronpedia

    INDEX
    Explanations

    specific types of relationships and entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irit
    -0.17
    itt
    -0.16
    boa
    -0.16
    usch
    -0.15
    irt
    -0.15
    rada
    -0.15
    ublished
    -0.14
    òa
    -0.14
    ifen
    -0.14
    ritt
    -0.14
    POSITIVE LOGITS
     upon
    0.50
    upon
    0.41
     Upon
    0.38
    Upon
    0.36
     cui
    0.34
     whom
    0.33
     whose
    0.33
     onto
    0.30
    whose
    0.28
     whence
    0.23
    Act Density 0.277%

    No Known Activations