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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the frequency or likelihood of occurrences in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Glas
    -0.16
    asje
    -0.16
    kel
    -0.15
    egan
    -0.15
    ibel
    -0.15
    cke
    -0.15
    aghan
    -0.15
    affe
    -0.15
    aire
    -0.15
    wagon
    -0.15
    POSITIVE LOGITS
     cases
    0.19
     Cases
    0.17
    Cases
    0.15
     situations
    0.15
     case
    0.15
    owitz
    0.14
     Case
    0.14
    cases
    0.14
    <header
    0.14
    732
    0.13
    Act Density 0.155%

    No Known Activations