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

    Neuronpedia

    INDEX
    Explanations

    instances of reported speech or quotations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yani
    -0.16
    ught
    -0.14
    heim
    -0.14
    #echo
    -0.14
     ourselves
    -0.14
    áo
    -0.14
    ãĥ«ãĥĪ
    -0.14
    Ỽ
    -0.14
    umo
    -0.13
    elle
    -0.13
    POSITIVE LOGITS
     although
    0.28
     there
    0.24
     while
    0.22
    :
    0.21
     since
    0.20
    although
    0.20
     besides
    0.20
     despite
    0.19
     Although
    0.18
     though
    0.18
    Act Density 0.123%

    No Known Activations