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

    Neuronpedia

    INDEX
    Explanations

    phrases related to displacement or movement of objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.74
    fully
    -0.67
    iam
    -0.65
    aroo
    -0.64
    bryce
    -0.64
    antes
    -0.63
    pers
    -0.63
    utm
    -0.63
     apiece
    -0.63
    /-
    -0.63
    POSITIVE LOGITS
     fray
    1.18
     bloodstream
    1.13
     realm
    1.07
     midst
    1.05
     depths
    1.03
     confines
    0.99
     realms
    0.96
     equation
    0.96
     forefront
    0.92
     vicinity
    0.92
    Act Density 0.211%

    No Known Activations