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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sports and games

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blank
    -0.70
    window
    -0.69
    Load
    -0.67
    mons
    -0.67
    Shut
    -0.67
    zip
    -0.66
    screen
    -0.64
    host
    -0.63
    Times
    -0.63
    LOCK
    -0.62
    POSITIVE LOGITS
     hence
    1.24
     consequently
    1.16
     therefore
    1.12
     secondly
    1.09
     thus
    1.05
     although
    0.95
     furthermore
    0.93
     then
    0.91
     moreover
    0.90
     thereby
    0.89
    Act Density 0.706%

    No Known Activations