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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "remaining."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.79
     poffible
    -0.69
     inalámbrica
    -0.68
     Houſe
    -0.67
     purpoſe
    -0.67
     atve
    -0.64
    ValueStyle
    -0.62
     صوتيه
    -0.61
     étoit
    -0.60
     pouvoit
    -0.60
    POSITIVE LOGITS
     Hum
    0.56
     Stanley
    0.50
    hum
    0.48
     remaining
    0.48
    Hum
    0.47
     mood
    0.46
    ones
    0.46
    HUM
    0.43
     gifted
    0.43
     Bridges
    0.42
    Act Density 0.163%

    No Known Activations