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

    Neuronpedia

    INDEX
    Explanations

    phrases related to current situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to the current state or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    formerly
    -0.82
    wright
    -0.81
    later
    -0.77
    another
    -0.75
     Previously
    -0.75
    then
    -0.74
    afort
    -0.70
     Yards
    -0.70
    else
    -0.70
    olean
    -0.70
    POSITIVE LOGITS
     incarnation
    1.35
     iteration
    1.26
     situation
    1.21
     predicament
    1.18
     spate
    1.13
     occupant
    1.06
     generation
    1.03
     crop
    1.02
     trajectory
    1.01
     edition
    0.98
    Act Density 0.047%

    No Known Activations