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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lists or enumerations

    oai_token-act-pair · gpt-3.5-turbo

    references to various unspecified items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irl
    -0.71
    inav
    -0.71
    strom
    -0.68
    oufl
    -0.66
    adia
    -0.66
    bern
    -0.65
     hom
    -0.65
    ECD
    -0.64
    oug
    -0.64
    sson
    -0.63
    POSITIVE LOGITS
     happening
    0.96
     happens
    0.92
     happen
    0.90
     happened
    0.87
     things
    0.85
     happ
    0.82
    Things
    0.81
     Happ
    0.77
    facts
    0.76
     matters
    0.76
    Act Density 0.037%

    No Known Activations