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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opinions or evaluations regarding achievements or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rypton
    -0.16
     OTHERWISE
    -0.14
     Aires
    -0.14
    ScrollIndicator
    -0.14
    rientation
    -0.14
    uctions
    -0.14
    indhoven
    -0.14
     Bid
    -0.14
    ellido
    -0.14
    ctors
    -0.14
    POSITIVE LOGITS
     critics
    0.22
     dÆ°
    0.22
     controversy
    0.21
     media
    0.21
     widespread
    0.20
     debate
    0.20
     talk
    0.20
     buzz
    0.20
     everyone
    0.20
     headlines
    0.19
    Act Density 0.011%

    No Known Activations