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

    Neuronpedia

    INDEX
    Explanations

    references to user-friendly features and functions of software or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     born
    -0.15
    oller
    -0.14
     pref
    -0.14
     nackte
    -0.14
    amo
    -0.14
     hale
    -0.14
    ansen
    -0.14
     tap
    -0.13
    313
    -0.13
     our
    -0.13
    POSITIVE LOGITS
    lights
    0.16
    bsites
    0.15
    icient
    0.15
    жд
    0.14
    rophe
    0.14
    RAINT
    0.14
    PLEX
    0.13
     lin
    0.13
    rego
    0.13
    oho
    0.13
    Act Density 0.024%

    No Known Activations