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

    Neuronpedia

    INDEX
    Explanations

    affirmative or positive assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riter
    -0.15
    ier
    -0.15
    xfff
    -0.14
    ãĥ©ãĥ¼
    -0.14
    askell
    -0.14
    mand
    -0.14
    ittel
    -0.13
    mandatory
    -0.13
     наб
    -0.13
     haline
    -0.13
    POSITIVE LOGITS
    /rss
    0.15
    xdb
    0.14
    XR
    0.14
    ãĥ¼ãĥijãĥ¼
    0.14
    ationship
    0.14
    lue
    0.14
    BOTTOM
    0.13
     mak
    0.13
    OSP
    0.13
    accom
    0.13
    Act Density 0.001%

    No Known Activations