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

    Neuronpedia

    INDEX
    Explanations

    phrases related to general agreement or collective opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essler
    -0.09
    leston
    -0.08
    erk
    -0.07
    bens
    -0.07
    Ñģлов
    -0.07
    -gnu
    -0.07
    енз
    -0.07
    erce
    -0.07
    resses
    -0.07
    ET
    -0.07
    POSITIVE LOGITS
     Reached
    0.09
     reached
    0.07
    Reached
    0.07
    ively
    0.07
     among
    0.07
    IONS
    0.07
     agreement
    0.07
     dÄ±ÅŁÄ±
    0.07
     Mechanics
    0.06
    igne
    0.06
    Act Density 0.005%

    No Known Activations