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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htaking
    -0.74
    ciating
    -0.66
    OTOS
    -0.64
     Moroc
    -0.62
    rote
    -0.61
     millenn
    -0.60
    ãĤ¼
    -0.60
     culminated
    -0.60
    ãĥĺãĥ©
    -0.60
    ãĤ¼ãĤ¦ãĤ¹
    -0.59
    POSITIVE LOGITS
     resign
    0.94
     intervene
    0.92
     gladly
    0.92
     forfeit
    0.91
     hesitate
    0.89
     immediately
    0.87
     abort
    0.85
     automatically
    0.84
     promptly
    0.82
     retaliate
    0.82
    Act Density 0.340%

    No Known Activations