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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or expressions of contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ipsum
    -0.68
    o
    -0.61
    NEXT
    -0.60
    cy
    -0.59
    いません
    -0.58
    WebControls
    -0.58
    Burt
    -0.58
    NavItem
    -0.57
    ItemData
    -0.56
    en
    -0.56
    POSITIVE LOGITS
     MonoBehaviour
    0.98
    ostante
    0.96
    though
    0.96
     although
    0.95
    although
    0.92
    theless
    0.92
    ureusement
    0.89
    Aunque
    0.89
    prüche
    0.88
    ewel
    0.88
    Act Density 0.058%

    No Known Activations