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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing disapproval or opposition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "objection" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rene
    -0.75
     ESV
    -0.71
    ching
    -0.68
    ectar
    -0.67
    roc
    -0.66
    alde
    -0.66
    tiny
    -0.66
    rio
    -0.64
     dime
    -0.64
    akin
    -0.64
    POSITIVE LOGITS
     objections
    1.24
     objection
    1.06
    ĸļ
    1.05
    naires
    1.00
     thereto
    0.82
     stren
    0.77
    swer
    0.76
     guiActiveUn
    0.76
     objected
    0.75
     vehemently
    0.74
    Act Density 0.013%

    No Known Activations