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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chicas
    -0.17
    uch
    -0.15
    lasses
    -0.15
    vvm
    -0.15
     нез
    -0.15
    pane
    -0.14
    girl
    -0.14
    æĬ¥åijĬ
    -0.13
    antar
    -0.13
    .Reporting
    -0.13
    POSITIVE LOGITS
     inher
    0.18
    олоÑģ
    0.15
    oshi
    0.15
    yx
    0.14
     Rex
    0.14
     impro
    0.14
    stin
    0.14
    ym
    0.14
     Urs
    0.14
    agn
    0.13
    Act Density 0.005%

    No Known Activations