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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to distinct categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åij½
    -0.16
    oten
    -0.15
    ocy
    -0.15
    antry
    -0.15
    uba
    -0.15
    .hw
    -0.15
    enson
    -0.15
     Laure
    -0.15
    UGE
    -0.15
     vess
    -0.14
    POSITIVE LOGITS
    izzie
    0.17
     Neutral
    0.16
    æĺ
    0.15
    caff
    0.15
    neutral
    0.15
     Hind
    0.15
     hind
    0.15
     Dog
    0.14
     Disorder
    0.14
     vui
    0.14
    Act Density 0.024%

    No Known Activations