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

    Neuronpedia

    INDEX
    Explanations

    references to changes or transformations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "change."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.82
     Bei
    -0.74
     ducks
    -0.67
    ross
    -0.66
     Purg
    -0.65
    vern
    -0.64
     LIMITED
    -0.63
     DRAGON
    -0.63
     Gerr
    -0.63
     Whale
    -0.63
    POSITIVE LOGITS
    over
    0.98
    overs
    0.92
     wrought
    0.85
     effected
    0.83
    able
    0.82
    making
    0.81
    agents
    0.79
    ials
    0.78
    xual
    0.78
    iations
    0.77
    Act Density 0.058%

    No Known Activations