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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social connections and community support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     however
    -0.17
    çĶļèĩ³
    -0.16
    igh
    -0.16
     therefore
    -0.16
    ropol
    -0.15
     should
    -0.15
     perhaps
    -0.15
     Shall
    -0.15
     wonder
    -0.15
    Should
    -0.15
    POSITIVE LOGITS
    æ¯ķ
    0.22
    already
    0.19
    åĺĽ
    0.19
     unlike
    0.18
    å®ŀåľ¨
    0.18
     already
    0.17
    æ¶ī
    0.16
     jinak
    0.15
     directly
    0.15
     tolik
    0.15
    Act Density 0.422%

    No Known Activations