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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons with other entities or things

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to technology and various industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Proxy
    -0.68
    steen
    -0.67
    instein
    -0.63
    arty
    -0.60
    yon
    -0.60
    oros
    -0.60
    enhagen
    -0.60
    CHAT
    -0.57
    enberg
    -0.56
     Correct
    -0.56
    POSITIVE LOGITS
     except
    0.78
     preceded
    0.73
    Tracker
    0.71
     besides
    0.71
     surveyed
    0.70
     whatsoever
    0.68
     nationwide
    0.68
     contemporaries
    0.68
     attRot
    0.67
     imaginable
    0.66
    Act Density 0.244%

    No Known Activations