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

    Neuronpedia

    INDEX
    Explanations

    keywords related to safety and performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etic
    -0.17
    ora
    -0.15
    ether
    -0.15
    (SIG
    -0.15
    itzer
    -0.15
     Hollow
    -0.14
    ORA
    -0.14
    ETHER
    -0.14
     Pandora
    -0.14
     uni
    -0.13
    POSITIVE LOGITS
    prene
    0.16
     BÃŃ
    0.15
    ihat
    0.15
    anvas
    0.14
    άνÏĦα
    0.14
    odem
    0.14
    oxy
    0.14
    esiz
    0.14
    locking
    0.14
    raised
    0.14
    Act Density 0.283%

    No Known Activations