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

    Neuronpedia

    INDEX
    Explanations

    terms related to processes and evaluations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Affairs
    -0.15
    ÏĥÏĦε
    -0.14
    gross
    -0.14
    _RENDERER
    -0.14
    ITHER
    -0.14
    -devel
    -0.14
    anka
    -0.14
    kea
    -0.14
    lish
    -0.13
     affairs
    -0.13
    POSITIVE LOGITS
    ForMember
    0.18
    hoot
    0.15
    ernen
    0.15
     Winn
    0.14
    forc
    0.14
    726
    0.14
    685
    0.14
    0.14
    aque
    0.13
    roe
    0.13
    Act Density 0.527%

    No Known Activations