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

    Neuronpedia

    INDEX
    Explanations

    dialogue indicating agreement or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    burn
    -0.18
    irie
    -0.15
    rient
    -0.15
    ouver
    -0.14
    pring
    -0.14
     Vent
    -0.14
    .opens
    -0.14
    ilter
    -0.14
    ourn
    -0.13
     tụ
    -0.13
    POSITIVE LOGITS
    osto
    0.17
    ographics
    0.15
    edral
    0.15
    183
    0.15
    signals
    0.15
     grow
    0.14
    sat
    0.14
    889
    0.14
    auty
    0.13
    371
    0.13
    Act Density 0.048%

    No Known Activations