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

    Neuronpedia

    INDEX
    Explanations

    references to a specific term, "Boilerplate"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Bo" and its contextual use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.83
    orial
    -0.82
    代
    -0.79
    terday
    -0.76
    rity
    -0.75
    ional
    -0.74
    UAL
    -0.71
    ablishment
    -0.70
    yrinth
    -0.68
    mary
    -0.67
    POSITIVE LOGITS
     Bo
    1.22
    Bo
    1.07
     Bagg
    1.05
    zz
    0.97
    zeb
    0.95
    zzi
    0.92
    zos
    0.90
    gey
    0.86
    iler
    0.86
    olean
    0.85
    Act Density 0.009%

    No Known Activations