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

    Neuronpedia

    INDEX
    Explanations

    statements asserting the truth of claims or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.64
    oredCriteria
    -0.63
    InjectAttribute
    -0.57
    >>>>>>>
    -0.54
     يتيمه
    -0.53
    ftagPool
    -0.52
    <bos>
    -0.52
    曖昧さ回避
    -0.51
    setVerticalGroup
    -0.51
    -0.49
    POSITIVE LOGITS
     true
    2.32
    true
    1.99
    True
    1.55
     TRUE
    1.54
     True
    1.54
    TRUE
    1.35
     vrai
    1.30
     truer
    1.25
     cierto
    1.22
     truest
    1.16
    Act Density 0.475%

    No Known Activations