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

    Neuronpedia

    INDEX
    Explanations

    references to communities and the interactions within them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morph
    -0.15
    ÄĽk
    -0.15
    morph
    -0.15
    arpa
    -0.14
     Lana
    -0.14
    atta
    -0.14
    одеÑĢж
    -0.14
     boz
    -0.14
    azor
    -0.14
    ufen
    -0.14
    POSITIVE LOGITS
    ailable
    0.18
     daily
    0.16
     Ellison
    0.15
     mere
    0.15
     cazzo
    0.14
     everyday
    0.14
    Priv
    0.14
     we
    0.14
     around
    0.13
    ç½®
    0.13
    Act Density 0.099%

    No Known Activations