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

    Neuronpedia

    INDEX
    Explanations

    words related to a high level of quality or intensity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "raw" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.87
    agements
    -0.71
    ŃĶ
    -0.70
    atural
    -0.68
    »Ĵ
    -0.67
    Ħ¢
    -0.65
    ippi
    -0.65
    uyomi
    -0.64
    pmwiki
    -0.64
    ajo
    -0.63
    POSITIVE LOGITS
    hide
    1.51
     sewage
    1.18
    ls
    1.17
    lins
    1.10
    lings
    1.08
     materials
    1.07
    esome
    0.89
    kus
    0.85
     denim
    0.82
     material
    0.82
    Act Density 0.027%

    No Known Activations