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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating communication or contact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACKET
    -0.17
    ompiler
    -0.16
    Forum
    -0.15
    typing
    -0.14
    ritz
    -0.14
    rud
    -0.14
     Dip
    -0.14
    iná
    -0.14
     ful
    -0.13
    illance
    -0.13
    POSITIVE LOGITS
     contact
    0.44
    contact
    0.36
     Contact
    0.33
     contacto
    0.32
    Contact
    0.31
     CONTACT
    0.31
     contacting
    0.31
     touch
    0.30
     Kontakt
    0.30
     contacted
    0.29
    Act Density 0.032%

    No Known Activations