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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to risking or compromising

    oai_token-act-pair · gpt-3.5-turbo

    terms related to risk and the act of revealing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.71
     Archangel
    -0.69
     Grail
    -0.67
     Crusader
    -0.65
    VIDEO
    -0.65
    OTA
    -0.64
     Saber
    -0.62
     Chronicle
    -0.61
    OPLE
    -0.61
    crop
    -0.61
    POSITIVE LOGITS
    ised
    1.25
    ising
    1.18
    icated
    1.12
    izing
    1.12
    ized
    1.11
    ues
    1.09
    isers
    1.07
    ization
    1.06
    izes
    1.04
    icating
    1.03
    Act Density 0.030%

    No Known Activations