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

    Neuronpedia

    INDEX
    Explanations

    sets of curly braces, indicating block structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     minus
    -0.74
     Christensen
    -0.69
    ので
    -0.64
     Eisenberg
    -0.63
     Steen
    -0.61
    urum
    -0.58
     of
    -0.58
    mels
    -0.58
    sme
    -0.57
    嚷
    -0.57
    POSITIVE LOGITS
    {
    1.50
    __':
    1.47
     {
    1.45
    __":
    1.44
    __':
    1.44
    --){
    1.43
    __":
    1.42
    "])){
    1.42
    (){
    1.40
    '])){
    1.37
    Act Density 0.158%

    No Known Activations