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

    Neuronpedia

    INDEX
    Explanations

    words related to positive attitudes or qualities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "spirit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Printed
    -0.81
     Parenthood
    -0.71
    PsyNetMessage
    -0.67
     Borderlands
    -0.63
     Bradford
    -0.62
     WATCHED
    -0.62
    riad
    -0.62
    DERR
    -0.61
    theless
    -0.59
     GPUs
    -0.58
    POSITIVE LOGITS
     spirit
    0.98
    uality
    0.93
    ierre
    0.86
    ewitness
    0.81
    atics
    0.81
    smanship
    0.80
    spirit
    0.77
    Spirit
    0.76
    uous
    0.75
    wagon
    0.74
    Act Density 0.006%

    No Known Activations