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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating universality or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     atmos
    -0.14
    oslav
    -0.14
    orthand
    -0.14
     koc
    -0.14
    prise
    -0.14
    ayıp
    -0.13
    urga
    -0.13
    lexport
    -0.13
    APPLE
    -0.13
    utz
    -0.13
    POSITIVE LOGITS
     centralized
    0.18
     proper
    0.18
     decentral
    0.15
     Proper
    0.14
    ifton
    0.14
     decentralized
    0.14
     ple
    0.14
    icht
    0.14
    iesel
    0.14
     Soccer
    0.14
    Act Density 0.000%

    No Known Activations