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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the process of becoming or starting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    libc
    -0.08
    rire
    -0.08
     porr
    -0.08
    asa
    -0.07
    ToJson
    -0.07
    rei
    -0.07
    rael
    -0.06
    terra
    -0.06
    amente
    -0.06
    acente
    -0.06
    POSITIVE LOGITS
     became
    0.08
     become
    0.07
     вообÑīе
    0.07
    \common
    0.06
    tings
    0.06
    oy
    0.06
     suddenly
    0.06
    bec
    0.06
     Became
    0.06
     à¤ĩतन
    0.06
    Act Density 0.016%

    No Known Activations