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

    Neuronpedia

    INDEX
    Explanations

    specific citations or references within articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è©
    -0.15
    idl
    -0.14
    ich
    -0.14
    iel
    -0.14
    olin
    -0.14
    rian
    -0.14
    ÏĦÏĥ
    -0.14
     Rod
    -0.13
     https
    -0.13
    anan
    -0.13
    POSITIVE LOGITS
    usic
    0.15
    Ïģθ
    0.14
    rand
    0.14
    омÑĸ
    0.14
    è³Ģ
    0.14
    letic
    0.14
    odable
    0.13
    enden
    0.13
    LARI
    0.13
     ------------------------------------------------------------------------↵
    0.13
    Act Density 0.047%

    No Known Activations