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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities preceded by the word "about" indicating approximate amounts or counts

    oai_token-act-pair · gpt-3.5-turbo

    quantitative metrics or numerical data within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bra
    -0.71
    dale
    -0.67
     Slime
    -0.67
     Doodle
    -0.63
     immortal
    -0.62
    thood
    -0.61
     Blues
    -0.60
     soar
    -0.60
    abee
    -0.60
     dearly
    -0.59
    POSITIVE LOGITS
     dozen
    0.85
    dozen
    0.84
     thous
    0.83
    OTAL
    0.75
    addons
    0.73
     hours
    0.73
     percent
    0.68
     hrs
    0.68
    uner
    0.64
    700
    0.64
    Act Density 0.184%

    No Known Activations