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

    Neuronpedia

    INDEX
    Explanations

    phrases related to addition or augmentation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "plus" indicating an addition or benefit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adr
    -0.89
    bris
    -0.86
    uchs
    -0.80
    gments
    -0.79
    atters
    -0.79
    rimp
    -0.77
    stem
    -0.76
    arer
    -0.74
    geons
    -0.74
    cci
    -0.73
    POSITIVE LOGITS
    minus
    0.85
    /-
    0.79
     plus
    0.77
     infinity
    0.77
     append
    0.76
    cules
    0.70
     PLUS
    0.69
    plus
    0.68
    /+
    0.66
    ++++
    0.65
    Act Density 0.012%

    No Known Activations