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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols commonly associated with data or programming

    oai_token-act-pair · gpt-3.5-turbo

    the special character "ÂŃ" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pestic
    -0.64
    çĶ°
    -0.62
    Reloaded
    -0.61
    åį
    -0.59
    DragonMagazine
    -0.58
     shack
    -0.57
     Hats
    -0.57
     mosqu
    -0.56
     handshake
    -0.56
     Skull
    -0.56
    POSITIVE LOGITS
    nesota
    0.83
    selves
    0.79
    la
    0.78
    tu
    0.71
    ith
    0.71
    late
    0.70
    po
    0.69
    tal
    0.69
    der
    0.68
    ten
    0.66
    Act Density 0.036%

    No Known Activations