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

    Neuronpedia

    INDEX
    Explanations

    phrases related to demonstration or presentation of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urette
    -0.17
    arro
    -0.16
     Q
    -0.16
    avra
    -0.15
    497
    -0.15
    felt
    -0.15
     Vor
    -0.14
    leigh
    -0.14
    zig
    -0.14
    kar
    -0.14
    POSITIVE LOGITS
     how
    0.22
    æĢİ
    0.17
    how
    0.17
     mercy
    0.17
    å¦Ĥä½ķ
    0.17
     cómo
    0.16
    oscope
    0.16
    rys
    0.15
     hoa
    0.15
    aise
    0.15
    Act Density 0.056%

    No Known Activations