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

    Neuronpedia

    INDEX
    Explanations

    locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convol
    -0.65
    wagon
    -0.60
    CLASSIFIED
    -0.60
    username
    -0.59
     thous
    -0.58
     awa
    -0.58
     destro
    -0.57
     lodged
    -0.56
     therein
    -0.56
     unemploy
    -0.56
    POSITIVE LOGITS
     lieu
    1.15
     accordance
    1.01
    clusions
    0.99
     conjunction
    0.98
    clus
    0.97
    ordinate
    0.93
    patient
    0.91
     vitro
    0.89
    humane
    0.88
     favor
    0.86
    Act Density 0.355%

    No Known Activations