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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .criteria
    -0.15
    olf
    -0.14
    orthy
    -0.14
    allis
    -0.14
    _Tis
    -0.14
     hers
    -0.14
     Managed
    -0.14
    ÑĪив
    -0.14
    ald
    -0.14
    yme
    -0.13
    POSITIVE LOGITS
     preferred
    0.31
    preferred
    0.26
     ideal
    0.26
     superior
    0.23
     prefer
    0.22
    ideal
    0.22
    Preferred
    0.22
     best
    0.21
     пÑĢедпоÑĩ
    0.21
     pref
    0.21
    Act Density 0.161%

    No Known Activations