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

    Neuronpedia

    INDEX
    Explanations

    words related to complaints or criticism

    oai_token-act-pair · gpt-3.5-turbo

    words related to complaints or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plane
    -0.64
    ²¾
    -0.62
     watered
    -0.61
     thinly
    -0.59
     racially
    -0.58
    yip
    -0.58
     pivot
    -0.58
     sal
    -0.57
     hormones
    -0.57
    pps
    -0.57
    POSITIVE LOGITS
    acent
    1.53
    icating
    1.53
    imentary
    1.35
    icates
    1.35
    icated
    1.34
    aints
    1.30
    icit
    1.27
    iance
    1.25
    ainer
    1.21
    aint
    1.21
    Act Density 0.032%

    No Known Activations