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

    Neuronpedia

    INDEX
    Explanations

    references to experiments and the outcomes related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guide
    -0.16
    arbonate
    -0.16
    åĪĢ
    -0.15
    ì°°
    -0.15
    levision
    -0.15
    ái
    -0.15
     guide
    -0.14
    rella
    -0.14
    esz
    -0.14
    orama
    -0.14
    POSITIVE LOGITS
     bÄĥng
    0.15
    datal
    0.14
    .rawValue
    0.14
    CEF
    0.14
     inject
    0.14
    æĺĵ
    0.14
    ì¶ľ
    0.14
    retain
    0.13
    олÑİ
    0.13
     LATIN
    0.13
    Act Density 0.349%

    No Known Activations