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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations or DOIs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    058
    -0.18
    essler
    -0.16
    engeance
    -0.15
     Pam
    -0.15
     spiral
    -0.15
     Pom
    -0.14
     Wheeler
    -0.14
     ts
    -0.14
    opal
    -0.14
    isper
    -0.14
    POSITIVE LOGITS
    عÛĮ
    0.16
    esModule
    0.15
    è¥
    0.15
    (DialogInterface
    0.14
    Exc
    0.14
    tep
    0.14
    سط
    0.14
     hạ
    0.14
    _exc
    0.14
    ÃŃv
    0.14
    Act Density 0.009%

    No Known Activations