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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating movement or change in location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "onto."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expensive
    -0.79
    enegger
    -0.75
    senal
    -0.67
    len
    -0.67
    eters
    -0.66
    friend
    -0.66
    orno
    -0.66
    erent
    -0.66
    zai
    -0.66
    clave
    -0.66
    POSITIVE LOGITS
     behalf
    0.88
     shore
    0.82
     rooft
    0.80
    pload
    0.78
    screen
    0.77
     occasion
    0.75
    itored
    0.73
     account
    0.73
    slaught
    0.70
     arrival
    0.68
    Act Density 0.014%

    No Known Activations