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

    Neuronpedia

    INDEX
    Explanations

    topics or phrases that are receiving a lot of attention or focus

    oai_token-act-pair · gpt-3.5-turbo

    topics related to attention and interest in various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blinding
    -0.60
    iannopoulos
    -0.59
    heid
    -0.57
    ritical
    -0.56
    viation
    -0.54
     ceremon
    -0.53
    ROR
    -0.53
    ocide
    -0.52
    ermanent
    -0.52
     unwitting
    -0.52
    POSITIVE LOGITS
     lately
    1.81
     nowadays
    1.66
     today
    1.27
     now
    1.14
     tonight
    1.10
     recently
    1.07
     right
    1.04
     these
    0.98
     currently
    0.95
    today
    0.88
    Act Density 0.636%

    No Known Activations