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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditionality and dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.59
     SwitchCompat
    -0.45
     ModelExpression
    -0.42
    ksamkeit
    -0.38
    setVerticalGroup
    -0.38
    FailureListener
    -0.38
     MotionEvent
    -0.37
    principalTable
    -0.37
    PutMapping
    -0.36
    IANGLES
    -0.35
    POSITIVE LOGITS
     circumstances
    1.02
     budget
    0.92
     circumstance
    0.85
     preferences
    0.85
     situation
    0.81
    situation
    0.81
     Circumstances
    0.80
     temperament
    0.79
     budgets
    0.78
    budget
    0.77
    Act Density 0.505%

    No Known Activations