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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or development in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" and its context within phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Champ
    -0.72
    Middle
    -0.67
    Solid
    -0.62
    ]}
    -0.62
    Americ
    -0.62
    cia
    -0.61
    Los
    -0.60
    FTWARE
    -0.60
    20439
    -0.59
    axis
    -0.59
    POSITIVE LOGITS
     fact
    0.85
     essence
    0.83
     effect
    0.74
    versely
    0.68
    escap
    0.68
    ev
    0.66
    ouver
    0.66
     principle
    0.65
    advert
    0.65
     vain
    0.64
    Act Density 0.146%

    No Known Activations