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

    Neuronpedia

    INDEX
    Explanations

    mentions of or related to heavy objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "heavy" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agos
    -0.75
     Jennings
    -0.70
    ISA
    -0.70
    ogle
    -0.68
     ren
    -0.67
     Reid
    -0.65
    ocrates
    -0.65
    ynski
    -0.64
     altru
    -0.64
     FDR
    -0.63
    POSITIVE LOGITS
     Heavy
    3.24
    Heavy
    3.00
    heavy
    2.93
     heavy
    2.30
     heavier
    2.15
     heaviest
    2.04
     heav
    1.35
     heavyweight
    1.29
    metal
    1.24
     lighter
    1.17
    Act Density 0.022%

    No Known Activations