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

    Neuronpedia

    INDEX
    Explanations

    proper names, particularly the name "Trevor."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Trevor" and "Vernon"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spring
    -0.78
    maid
    -0.76
    organic
    -0.74
    arching
    -0.74
     responsive
    -0.71
    iggs
    -0.69
    flu
    -0.68
    ĺħ
    -0.66
     actionGroup
    -0.66
    ItemImage
    -0.66
    POSITIVE LOGITS
     Trevor
    1.33
     Noah
    0.89
     Philips
    0.88
     Meier
    0.85
     Damon
    0.84
     Siem
    0.83
     Smy
    0.82
     Thornton
    0.82
     Beau
    0.82
     Nolan
    0.81
    Act Density 0.010%

    No Known Activations