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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance evaluation and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plib
    -0.16
    UFFER
    -0.15
    ULA
    -0.15
    baz
    -0.15
    ît
    -0.14
    ies
    -0.14
     Tin
    -0.14
    iffies
    -0.14
    placer
    -0.14
    uffer
    -0.14
    POSITIVE LOGITS
    ringe
    0.18
    eru
    0.16
    afc
    0.15
    eve
    0.14
    ParameterValue
    0.14
    lon
    0.14
     formations
    0.14
    wo
    0.14
    forge
    0.13
     refere
    0.13
    Act Density 0.030%

    No Known Activations