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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease of completing tasks or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĤв
    -0.17
    usty
    -0.15
     conserv
    -0.15
     k
    -0.15
     bigger
    -0.14
     branch
    -0.14
     needed
    -0.14
     to
    -0.14
     Routes
    -0.14
    _MODAL
    -0.14
    POSITIVE LOGITS
     easier
    0.30
     ease
    0.27
     Ease
    0.25
    _easy
    0.21
    Ease
    0.21
     easy
    0.20
     easiest
    0.20
    easy
    0.20
    ease
    0.20
     eas
    0.19
    Act Density 0.073%

    No Known Activations