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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating sets of items or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubi
    -0.16
     Freeze
    -0.14
    á»ķng
    -0.14
    ãĥĥãĥī
    -0.14
     Teddy
    -0.14
    Ĩµ
    -0.14
     Pad
    -0.13
     PAD
    -0.13
    -to
    -0.13
    487
    -0.13
    POSITIVE LOGITS
    opia
    0.15
    appen
    0.15
    PECIAL
    0.14
    -License
    0.14
     accommodation
    0.14
    lish
    0.14
    áte
    0.14
    fahren
    0.13
    anken
    0.13
    SIDE
    0.13
    Act Density 0.011%

    No Known Activations