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

    Neuronpedia

    INDEX
    Explanations

    references to legal agreements and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ig
    -0.15
    ade
    -0.15
    erra
    -0.15
    iese
    -0.15
    Å¡lo
    -0.14
    atches
    -0.14
    rek
    -0.14
     nude
    -0.14
    asar
    -0.13
    kt
    -0.13
    POSITIVE LOGITS
    /ag
    0.18
     Brow
    0.15
    access
    0.15
     Agree
    0.15
     accessing
    0.14
     agreeing
    0.14
     govern
    0.14
     access
    0.14
    едак
    0.14
     Terms
    0.14
    Act Density 0.022%

    No Known Activations