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

    Neuronpedia

    INDEX
    Explanations

    phrases related to standing one's ground or being assertive

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating resistance or defiance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teenth
    -0.79
    swick
    -0.78
    tained
    -0.73
    jas
    -0.71
    among
    -0.71
    tainment
    -0.71
    agues
    -0.71
    erve
    -0.70
    marks
    -0.70
    nesota
    -0.68
    POSITIVE LOGITS
     disav
    0.77
     hesitate
    0.76
     blindly
    0.75
     withdrawals
    0.74
     apologise
    0.74
     urge
    0.73
     bandwagon
    0.73
     shaky
    0.72
     ideologically
    0.72
     disbelief
    0.71
    Act Density 0.142%

    No Known Activations