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

    Neuronpedia

    INDEX
    Explanations

    genres and classification labels related to media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hack
    -0.19
    Hack
    -0.17
    hack
    -0.16
    ccak
    -0.16
     Hack
    -0.16
    ottes
    -0.15
    Ļ¨
    -0.15
    ocache
    -0.14
    497
    -0.14
    plorer
    -0.14
    POSITIVE LOGITS
    zimmer
    0.15
    icho
    0.14
    ständ
    0.14
    tee
    0.14
    ãĥ¯ãĤ¤ãĥĪ
    0.13
    гоÑĢ
    0.13
    ph
    0.13
    802
    0.13
    .pb
    0.13
     Atom
    0.13
    Act Density 0.006%

    No Known Activations