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

    Neuronpedia

    INDEX
    Explanations

    common prepositions and verbs related to requests and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anh
    -0.17
     Houses
    -0.15
    QL
    -0.15
    anoia
    -0.14
    spell
    -0.14
    phia
    -0.14
    ULA
    -0.14
    ibar
    -0.14
    imap
    -0.14
    ba
    -0.14
    POSITIVE LOGITS
     mú
    0.19
    íĥģ
    0.17
     endless
    0.17
     multiple
    0.17
    ãĥĨãĥ«
    0.17
     invasive
    0.16
    ç¹ģ
    0.16
    multiple
    0.15
     complex
    0.15
    Verbose
    0.15
    Act Density 0.003%

    No Known Activations