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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating disruption or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndPassword
    -0.17
    irth
    -0.16
    aeper
    -0.16
    hone
    -0.16
    /from
    -0.15
    .idea
    -0.15
    aura
    -0.15
    exterity
    -0.14
    OUTH
    -0.14
     Dispose
    -0.14
    POSITIVE LOGITS
     havoc
    0.18
    feld
    0.17
    à¹Ģà¸ģà¸Ńร
    0.16
    water
    0.15
    age
    0.15
    Ł
    0.15
    Toast
    0.15
    umont
    0.14
    NCY
    0.14
    staff
    0.14
    Act Density 0.079%

    No Known Activations