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

    Neuronpedia

    INDEX
    Explanations

    positive and negative news statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Downing
    -0.15
     after
    -0.15
     Ble
    -0.14
    коз
    -0.14
     if
    -0.14
     Nations
    -0.14
     force
    -0.14
     see
    -0.13
    anas
    -0.13
     unless
    -0.13
    POSITIVE LOGITS
    ucc
    0.16
    oldur
    0.16
    urname
    0.15
    agli
    0.15
    erule
    0.15
    Narrated
    0.15
    åįĵ
    0.15
    owy
    0.14
    .uf
    0.14
    owe
    0.14
    Act Density 0.015%

    No Known Activations