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

    Neuronpedia

    INDEX
    Explanations

    the infinitive form of verbs indicating actions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behold
    -0.16
    aad
    -0.16
    ange
    -0.15
    ersh
    -0.15
    eker
    -0.14
    audi
    -0.14
     Coun
    -0.14
    ught
    -0.14
    ustry
    -0.14
    Ñĥй
    -0.14
    POSITIVE LOGITS
    dio
    0.16
     Kimber
    0.14
    agrams
    0.14
     éħ
    0.13
    éĢĶ
    0.13
     Dram
    0.13
    azine
    0.13
    ãĥĬãĥ«
    0.13
    izr
    0.13
    ournals
    0.12
    Act Density 0.120%

    No Known Activations