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

    Neuronpedia

    INDEX
    Explanations

    key points or themes related to identity and societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    νια
    -0.17
    .nih
    -0.16
    agos
    -0.16
    OUCH
    -0.16
    agit
    -0.15
    UMMY
    -0.15
     Trot
    -0.15
    :maj
    -0.14
    ouch
    -0.14
    ãģ»ãģĨ
    -0.14
    POSITIVE LOGITS
     anything
    0.17
    oÄį
    0.16
    qt
    0.16
     ever
    0.15
     EVER
    0.15
     anymore
    0.15
    ured
    0.15
    anything
    0.14
     anywhere
    0.14
    Tomorrow
    0.14
    Act Density 0.157%

    No Known Activations