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

    Neuronpedia

    INDEX
    Explanations

    phrases and commands related to checking or verifying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.48
     “
    -0.45
     
    -0.44
     Pen
    -0.43
    ↵↵↵
    -0.42
    amssymb
    -0.41
    यु
    -0.41
    FEAT
    -0.40
     N
    -0.40
    ↵↵↵↵
    -0.40
    POSITIVE LOGITS
     Checking
    1.57
     checking
    1.54
     checked
    1.52
     Checked
    1.52
    Checking
    1.42
     CHECK
    1.41
    checking
    1.39
     checks
    1.36
     check
    1.32
    checked
    1.30
    Act Density 0.156%

    No Known Activations