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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative reactions or opposition

    oai_token-act-pair · gpt-3.5-turbo

    mentions of backlash or negative reactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -1.01
    ogo
    -0.81
    estones
    -0.73
    ramer
    -0.72
    estone
    -0.70
    aple
    -0.69
    uchin
    -0.68
    olesterol
    -0.66
    ete
    -0.64
    ilk
    -0.63
    POSITIVE LOGITS
     backlash
    1.08
    lash
    1.04
     against
    0.81
     harshly
    0.78
     fury
    0.78
     reaction
    0.78
    naire
    0.76
     reactions
    0.76
     retaliation
    0.75
     fallout
    0.74
    Act Density 0.019%

    No Known Activations