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

    Neuronpedia

    INDEX
    Explanations

    words related to expressions of disagreement or opposition

    oai_token-act-pair · gpt-3.5-turbo

    expressions of dissent and opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.83
     Parenthood
    -0.78
     livest
    -0.74
    onut
    -0.72
    amera
    -0.72
    ewater
    -0.70
    api
    -0.70
    è¦ļéĨĴ
    -0.69
    oshop
    -0.68
    estone
    -0.64
    POSITIVE LOGITS
     rebellion
    0.88
    backer
    0.77
     revolt
    0.76
     rebellious
    0.76
    ighters
    0.75
    bryce
    0.74
    edient
    0.74
     Rebell
    0.71
     legion
    0.71
    uous
    0.70
    Act Density 0.130%

    No Known Activations