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

    Neuronpedia

    INDEX
    Explanations

    references related to drowning or suffocation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drowning or references to water-related fatalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Collider
    -0.69
    rity
    -0.68
    WB
    -0.63
    ################
    -0.61
     deviation
    -0.60
     Publishers
    -0.60
    appro
    -0.59
     permissions
    -0.59
     alignment
    -0.58
    rian
    -0.58
    POSITIVE LOGITS
     drown
    1.17
     drowning
    1.10
     drowned
    0.93
    leneck
    0.79
    oling
    0.77
     overboard
    0.72
    ©¶æ¥µ
    0.71
    lect
    0.71
    bank
    0.70
    icates
    0.70
    Act Density 0.006%

    No Known Activations