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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight relationships and community structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PRESSION
    -0.14
    à¹Ĩ
    -0.14
    _projection
    -0.14
    464
    -0.14
     Leah
    -0.14
     à¹Ĩ
    -0.14
    pressor
    -0.13
    ollah
    -0.13
     sublicense
    -0.13
    ož
    -0.13
    POSITIVE LOGITS
    rzy
    0.15
    isy
    0.14
     Flake
    0.14
    apesh
    0.14
    eniable
    0.14
    xae
    0.13
    ESH
    0.13
    ű
    0.13
    ienie
    0.13
    ETHOD
    0.13
    Act Density 0.196%

    No Known Activations