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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -1.31
    Personendaten
    -1.14
    ConstraintMaker
    -1.14
     AssemblyTitle
    -1.10
    endpush
    -1.04
    DockStyle
    -1.01
    IntoConstraints
    -0.99
    AsUp
    -0.94
     resourceCulture
    -0.94
    الإنجليزية
    -0.92
    POSITIVE LOGITS
    推
    0.50
     note
    0.49
    สัง
    0.48
     question
    0.46
     remember
    0.45
     look
    0.43
     imagine
    0.43
     notice
    0.43
     remarque
    0.42
    澄
    0.42
    Act Density 0.720%

    No Known Activations