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

    Neuronpedia

    INDEX
    Explanations

    references to significant violent events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sized
    -0.68
     congress
    -0.67
     thumbnail
    -0.66
     Pand
    -0.65
     figure
    -0.65
     caf
    -0.64
     likeness
    -0.63
     match
    -0.63
     Bund
    -0.62
     PATH
    -0.62
    POSITIVE LOGITS
    hov
    1.07
    hi
    0.86
    staking
    0.84
    stress
    0.78
    peria
    0.75
    orthodox
    0.75
    iko
    0.74
    fter
    0.74
    pin
    0.72
    ounding
    0.72
    Act Density 0.216%

    No Known Activations