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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating examples or instances of something

    oai_token-act-pair · gpt-3.5-turbo

    instances where a concept or phenomenon is referred to as an example

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.77
    urses
    -0.69
    quire
    -0.69
    ties
    -0.69
    ief
    -0.68
    resent
    -0.66
    ouls
    -0.65
    ternity
    -0.64
    rice
    -0.63
    tones
    -0.63
    POSITIVE LOGITS
     illustrating
    1.03
     thereof
    0.94
     examples
    0.84
     demonstrating
    0.77
     of
    0.76
    wcsstore
    0.76
     illustration
    0.74
    baugh
    0.74
     illustrates
    0.73
     exempl
    0.73
    Act Density 0.047%

    No Known Activations