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

    Neuronpedia

    INDEX
    Explanations

    terms related to connections and associations between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vv
    -0.16
    agement
    -0.16
    aging
    -0.16
    éłŃ
    -0.15
    pir
    -0.15
    _THAT
    -0.15
    inters
    -0.14
    ноÑĩ
    -0.14
    ëĪĦ
    -0.14
    iza
    -0.14
    POSITIVE LOGITS
     somehow
    0.22
     directly
    0.21
     closely
    0.18
    irect
    0.17
    sian
    0.16
    linked
    0.16
     пÑĢÑıмо
    0.16
    ëŀĮ
    0.15
    OMATIC
    0.15
     linked
    0.15
    Act Density 0.058%

    No Known Activations