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

    Neuronpedia

    INDEX
    Explanations

    numerical representations of data, particularly percentages or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enden
    -0.18
    AdapterFactory
    -0.15
    ependency
    -0.15
    reen
    -0.14
    ibbon
    -0.14
    óc
    -0.14
     Matthias
    -0.14
    rees
    -0.13
    scoped
    -0.13
    reau
    -0.13
    POSITIVE LOGITS
    quel
    0.18
    ANJI
    0.16
    ickle
    0.15
    xfff
    0.14
     Malone
    0.13
    atican
    0.13
    亡
    0.13
    /dom
    0.13
    zsche
    0.13
    _DSP
    0.13
    Act Density 0.125%

    No Known Activations