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

    Neuronpedia

    INDEX
    Explanations

    scholarly references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vro
    -0.18
    abez
    -0.15
    abay
    -0.15
    ÑĢÑĸп
    -0.15
    èĽĭ
    -0.15
    cak
    -0.15
    eneg
    -0.15
    PERTIES
    -0.14
    stalk
    -0.14
    orsk
    -0.14
    POSITIVE LOGITS
    ilar
    0.16
    æķ£
    0.16
     subt
    0.15
    apis
    0.15
    iar
    0.14
    eka
    0.14
    argon
    0.13
    лÑĥÑĩ
    0.13
    /prom
    0.13
     outgoing
    0.13
    Act Density 0.071%

    No Known Activations