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

    Neuronpedia

    INDEX
    Explanations

    mentions of familial or affectionate terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htdocs
    -0.15
     GOODMAN
    -0.15
    ãĤ
    -0.14
     Gul
    -0.14
     open
    -0.14
     åĦ
    -0.14
     Goodman
    -0.13
    à¸Ļา
    -0.13
    PRETTY
    -0.13
    -Assad
    -0.13
    POSITIVE LOGITS
    ogl
    0.15
     Hlav
    0.15
    aut
    0.14
    ominated
    0.14
    vo
    0.14
     Cush
    0.14
    bed
    0.14
     fung
    0.14
    grav
    0.13
    uda
    0.13
    Act Density 0.049%

    No Known Activations