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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "yet" and its variations, indicating a focus on contrasting or juxtaposing ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aggio
    -0.16
    opers
    -0.15
    ught
    -0.14
    ddit
    -0.14
    oley
    -0.14
    iginal
    -0.14
     ELSE
    -0.14
    erd
    -0.14
    atern
    -0.13
    ledo
    -0.13
    POSITIVE LOGITS
     somehow
    0.27
    ting
    0.24
    ters
    0.21
    tings
    0.20
    forth
    0.20
    ter
    0.20
     Somehow
    0.19
    ta
    0.19
    -to
    0.17
     despite
    0.17
    Act Density 0.022%

    No Known Activations