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

    Neuronpedia

    INDEX
    Explanations

    instances where there is an intensification or increase in action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "step up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iw
    -0.73
    iop
    -0.66
    gemony
    -0.65
    >[
    -0.65
    ooo
    -0.64
    pers
    -0.62
    iol
    -0.62
    LEY
    -0.62
    #$
    -0.61
    ANS
    -0.61
    POSITIVE LOGITS
    stairs
    0.86
    river
    0.80
    steen
    0.74
    dates
    0.74
    grading
    0.73
     compr
    0.68
    grades
    0.67
     exponentially
    0.65
    dating
    0.64
    cycles
    0.63
    Act Density 0.041%

    No Known Activations