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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their relationships within a specified context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lørdag
    -0.64
     concentrated
    -0.55
     chré
    -0.55
     meeste
    -0.54
     flesta
    -0.53
     hunne
    -0.53
     kautta
    -0.53
     concentrating
    -0.52
    THURSDAY
    -0.52
     prenn
    -0.52
    POSITIVE LOGITS
     allegedly
    0.92
     reportedly
    0.86
     famously
    0.84
     controversi
    0.72
     compared
    0.70
     accidentally
    0.69
     threatened
    0.69
     supposedly
    0.67
    差点
    0.67
     hil
    0.66
    Act Density 0.555%

    No Known Activations