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

    Neuronpedia

    INDEX
    Explanations

    references to noise and looping structures in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.45
    SequentialGroup
    -0.45
     Taktlose
    -0.44
    parseColor
    -0.43
     Mayr
    -0.42
    Scottish
    -0.42
     "..\..\
    -0.42
    RUnlock
    -0.41
    isexual
    -0.40
    Lähteet
    -0.38
    POSITIVE LOGITS
     Loop
    0.86
     loop
    0.86
    Loop
    0.81
     noise
    0.80
     loops
    0.75
     Loops
    0.75
    loop
    0.69
    LOOP
    0.67
     Noise
    0.66
     sentiment
    0.66
    Act Density 0.078%

    No Known Activations