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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements and command settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antage
    -0.16
     ë°Ķë¡ľ
    -0.15
    еÑģÑĤÑĮ
    -0.14
    Unnamed
    -0.14
     Mount
    -0.14
     magna
    -0.14
    izzy
    -0.14
    #__
    -0.14
    umer
    -0.14
    ponsive
    -0.13
    POSITIVE LOGITS
    Ľå»º
    0.16
     kingdoms
    0.13
     tracked
    0.13
    rones
    0.13
    466
    0.13
     Stealth
    0.13
    iang
    0.13
    noise
    0.13
     //
    0.13
     liberal
    0.13
    Act Density 0.030%

    No Known Activations