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

    Neuronpedia

    INDEX
    Explanations

    phrases inviting the audience to engage or connect, often seen as "feel free."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egral
    -0.15
    isha
    -0.15
    fft
    -0.15
     ^{°}
    -0.15
     WARRANT
    -0.15
    ISTER
    -0.15
    agua
    -0.15
    zung
    -0.14
    ÑĢож
    -0.14
    sak
    -0.14
    POSITIVE LOGITS
    135
    0.16
    adge
    0.15
     cond
    0.14
    97
    0.14
     waived
    0.13
     DropIndex
    0.13
    EDA
    0.13
    aby
    0.13
     chained
    0.13
    103
    0.13
    Act Density 0.010%

    No Known Activations