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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers and attributes related to code and programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [...]
    -0.65
    �
    -0.58
     
    -0.53
     
    -0.51
    -0.51
    .***
    -0.48
    

    -0.47
    【
    -0.47
    .";
    -0.45
    )^{
    -0.44
    POSITIVE LOGITS
     _
    2.73
    (_
    2.62
     (_
    2.58
    =_
    2.46
    :_
    2.43
    ,_
    2.42
     &_
    2.35
    [_
    2.31
     !_
    2.30
     [_
    2.29
    Act Density 0.598%

    No Known Activations