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

    Neuronpedia

    INDEX
    Explanations

    terms related to commitment and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hart
    -0.18
    kla
    -0.15
    swire
    -0.15
    Į
    -0.15
    ][/
    -0.15
    ¶ļ
    -0.14
     UClass
    -0.14
    fir
    -0.14
    .ali
    -0.14
    paralle
    -0.14
    POSITIVE LOGITS
    Ùª
    0.16
    rz
    0.15
    eriod
    0.15
     Hood
    0.14
    tones
    0.14
     Peel
    0.14
    ös
    0.14
    aris
    0.13
    بÙĩ
    0.13
    avid
    0.13
    Act Density 0.552%

    No Known Activations