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

    Neuronpedia

    INDEX
    Explanations

    instances of specific affixes and their variations in the context of a conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequence after time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fubject
    -0.57
     purpoſe
    -0.54
     itſelf
    -0.50
     ſtand
    -0.49
     pleaſure
    -0.49
     ſta
    -0.46
     ſche
    -0.44
    XtraBars
    -0.43
    wiſe
    -0.42
     diſt
    -0.42
    POSITIVE LOGITS
     after
    1.41
     After
    1.38
    after
    1.36
    After
    1.33
     AFTER
    1.29
     dopo
    1.27
     após
    1.22
     після
    1.20
    AFTER
    1.20
     после
    1.18
    Act Density 0.007%

    No Known Activations