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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or places

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.79
    RIC
    -0.77
    lessly
    -0.75
    thood
    -0.75
    beard
    -0.73
    bear
    -0.72
    ventus
    -0.71
    ties
    -0.70
    LOCK
    -0.67
    wine
    -0.66
    POSITIVE LOGITS
     basis
    1.24
     sidelines
    1.22
     periphery
    1.21
     occasion
    1.21
     verge
    1.17
     brink
    1.17
     heels
    1.15
     outskirts
    1.14
     doorstep
    1.06
     same
    1.06
    Act Density 0.194%

    No Known Activations