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

    Neuronpedia

    INDEX
    Explanations

    references to building and improving chatbot systems and their associated techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /vnd
    -0.16
    _pickle
    -0.15
    ober
    -0.14
     ÐŁÑĢа
    -0.14
     Exercise
    -0.14
     goodness
    -0.14
    iliz
    -0.14
     Machine
    -0.14
    ignum
    -0.14
     Wol
    -0.14
    POSITIVE LOGITS
     pseudo
    0.18
     attention
    0.18
     Attention
    0.17
    SSL
    0.16
     losses
    0.15
     module
    0.15
    ä¼
    0.15
     pretext
    0.15
    seudo
    0.15
    -anchor
    0.15
    Act Density 0.007%

    No Known Activations