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

    Neuronpedia

    INDEX
    Explanations

    formatting elements and links commonly found in structured documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bilg
    -0.16
    akedown
    -0.15
    ults
    -0.14
    eres
    -0.14
    ramer
    -0.14
    ety
    -0.14
    ixo
    -0.13
     stor
    -0.13
    .problem
    -0.13
    PEAR
    -0.13
    POSITIVE LOGITS
    roz
    0.16
    ModelProperty
    0.16
    ail
    0.15
    /lg
    0.14
    asley
    0.14
    npos
    0.14
    alion
    0.14
    æİĽ
    0.14
     mouseY
    0.14
    éĿ
    0.13
    Act Density 0.020%

    No Known Activations