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

    Neuronpedia

    INDEX
    Explanations

    text related to additional features or bonuses

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words that contain the concept of "plus" or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adr
    -0.86
    arer
    -0.76
    lied
    -0.74
    oder
    -0.73
    ayn
    -0.73
    jar
    -0.71
    bris
    -0.71
    nce
    -0.70
    atters
    -0.69
    elly
    -0.69
    POSITIVE LOGITS
    minus
    1.05
     PLUS
    0.92
     plus
    0.91
    cules
    0.83
     minus
    0.74
     Ukrain
    0.74
    Plus
    0.71
    /-
    0.70
     Plus
    0.69
    FontSize
    0.69
    Act Density 0.008%

    No Known Activations