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

    Neuronpedia

    INDEX
    Explanations

    phrases and adverbs indicating additional or related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     allerdings
    -0.17
     meanwhile
    -0.17
    amen
    -0.16
     however
    -0.15
    nte
    -0.14
    pong
    -0.14
     either
    -0.13
    çĦ¶èĢĮ
    -0.13
    nt
    -0.13
     HOWEVER
    -0.13
    POSITIVE LOGITS
     importantly
    0.20
    ebek
    0.18
    forth
    0.17
    vice
    0.16
     vice
    0.16
    /OR
    0.16
    eyen
    0.15
    yre
    0.14
    GRE
    0.14
    -ÑĤаки
    0.14
    Act Density 0.182%

    No Known Activations