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

    Neuronpedia

    INDEX
    Explanations

    the word "backlash"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to backlash and public outcry against various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.96
    estone
    -0.81
    ogo
    -0.80
    estones
    -0.79
    uchin
    -0.78
    ramid
    -0.75
    aple
    -0.74
    ilts
    -0.73
    aky
    -0.71
    glas
    -0.71
    POSITIVE LOGITS
     backlash
    1.27
    lash
    1.00
     outcry
    0.84
     retaliate
    0.82
     fallout
    0.82
     uproar
    0.81
     reactions
    0.81
     reaction
    0.78
     homophobic
    0.78
     feedback
    0.77
    Act Density 0.008%

    No Known Activations