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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the existence or non-existence of various entities

    oai_token-act-pair · gpt-3.5-turbo

    references to existence or the concept of existing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.71
    edo
    -0.65
    Thom
    -0.65
    wer
    -0.63
     broom
    -0.62
    imar
    -0.62
     upgr
    -0.62
    bill
    -0.61
    Dro
    -0.60
    ney
    -0.60
    POSITIVE LOGITS
    entially
    1.06
    entials
    0.98
    places
    0.82
    nces
    0.78
    ential
    0.77
     existed
    0.77
     within
    0.76
     exists
    0.72
     peacefully
    0.71
    ences
    0.71
    Act Density 0.045%

    No Known Activations