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

    Neuronpedia

    INDEX
    Explanations

    programming and technical terms related to permissions and global variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enville
    -0.16
    pector
    -0.15
    opis
    -0.14
    émon
    -0.14
    echa
    -0.14
     Slut
    -0.13
    ragen
    -0.13
    odo
    -0.13
    ünde
    -0.13
    RY
    -0.13
    POSITIVE LOGITS
    wick
    0.17
    íĻĶ
    0.14
    ho
    0.14
     Brewer
    0.14
     trend
    0.14
     æ°¸
    0.14
    _ALIGNMENT
    0.14
     vita
    0.14
    εδ
    0.14
    ger
    0.13
    Act Density 0.029%

    No Known Activations