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

    Neuronpedia

    INDEX
    Explanations

    references to professions and professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ville
    -0.19
    ubar
    -0.15
    ophobia
    -0.15
    ogle
    -0.14
    esta
    -0.14
    ogg
    -0.14
    ippi
    -0.14
     slow
    -0.14
    meer
    -0.14
    ̣
    -0.14
    POSITIVE LOGITS
    regor
    0.19
    ABS
    0.15
    rad
    0.15
    nad
    0.14
     Raphael
    0.14
    ëŀĮ
    0.14
    948
    0.14
    YLE
    0.13
    elon
    0.13
    IVAL
    0.13
    Act Density 1.186%

    No Known Activations