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

    Neuronpedia

    INDEX
    Explanations

    specific individuals or professions within different scenarios, such as a film project or a criminal investigation

    oai_token-act-pair · gpt-3.5-turbo

    past tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.70
    ews
    -0.69
    ories
    -0.69
    snap
    -0.68
    lag
    -0.66
    ossom
    -0.66
     overtake
    -0.65
    where
    -0.65
    estyles
    -0.64
     Tags
    -0.63
    POSITIVE LOGITS
     unaware
    0.95
     hired
    0.87
     identified
    0.85
     blinded
    0.83
     aware
    0.83
     asleep
    0.81
     named
    0.81
     inexperienced
    0.81
    wolves
    0.80
     able
    0.80
    Act Density 0.360%

    No Known Activations