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

    Neuronpedia

    INDEX
    Explanations

    terms related to optimization and choosing options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    housing
    -0.15
    IPS
    -0.14
    ança
    -0.14
    ly
    -0.14
    hamster
    -0.14
    Ñħови
    -0.14
    оÑģÑĤÑĮ
    -0.14
    rp
    -0.13
    hana
    -0.13
    sworth
    -0.13
    POSITIVE LOGITS
    -out
    0.18
    \OptionsResolver
    0.16
    ört
    0.15
    imum
    0.15
    -Out
    0.15
    /opt
    0.15
    ayout
    0.15
    -in
    0.14
    oppins
    0.14
    avers
    0.14
    Act Density 0.023%

    No Known Activations