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

    Neuronpedia

    INDEX
    Explanations

    references to recent blog posts and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ini
    -0.14
    orig
    -0.14
    alem
    -0.14
    Ä©
    -0.14
    â
    -0.14
     Advance
    -0.14
    ç¾½
    -0.14
     flo
    -0.13
    ocrates
    -0.13
     advance
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĥĦ
    0.17
     Bash
    0.15
     tang
    0.15
    oksen
    0.15
     earlier
    0.15
    tainment
    0.14
    æk
    0.14
    ç§
    0.14
    lify
    0.14
     æ¹
    0.14
    Act Density 0.221%

    No Known Activations