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

    Neuronpedia

    INDEX
    Explanations

    quantities and numerical references related to people and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     almost
    -0.16
    xis
    -0.15
    efa
    -0.14
    iddi
    -0.14
    igos
    -0.14
    almost
    -0.13
    965
    -0.13
    èĩ³å°ij
    -0.13
     sid
    -0.13
     conservative
    -0.13
    POSITIVE LOGITS
     handful
    0.25
     thôi
    0.22
    羣æŃ£
    0.21
     ever
    0.21
     (<
    0.20
    ONLY
    0.19
    few
    0.19
     EVER
    0.19
     fewer
    0.18
    ãģĹãģĭ
    0.18
    Act Density 0.163%

    No Known Activations