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

    Neuronpedia

    INDEX
    Explanations

    terms related to significant global health and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æŃ
    -0.15
    UMP
    -0.15
     offending
    -0.14
     Hodg
    -0.14
    tlement
    -0.14
    ampus
    -0.14
    sez
    -0.14
    peg
    -0.14
    olar
    -0.13
     misunderstand
    -0.13
    POSITIVE LOGITS
     threat
    0.34
     problem
    0.25
     Threat
    0.24
     serious
    0.24
     threats
    0.22
     issue
    0.22
     ticking
    0.21
     concern
    0.21
    threat
    0.21
     scour
    0.20
    Act Density 0.075%

    No Known Activations