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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sizes, comparison, and groups of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    connections between large and small entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rabbit
    -0.70
     Reilly
    -0.69
     McAuliffe
    -0.68
    Hack
    -0.67
     Nieto
    -0.67
     Wilde
    -0.66
     Grail
    -0.66
     Lite
    -0.65
     Valkyrie
    -0.65
     Chau
    -0.63
    POSITIVE LOGITS
     arsen
    0.94
    anguage
    0.81
    ategories
    0.79
     Islands
    0.76
    hran
    0.75
    yz
    0.75
    cules
    0.74
    ritical
    0.72
    cious
    0.71
    alle
    0.71
    Act Density 0.258%

    No Known Activations