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

    Neuronpedia

    INDEX
    Explanations

    words related to negative societal or environmental issues

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various forms of environmental and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihad
    -0.62
    earcher
    -0.59
     Source
    -0.57
    organic
    -0.56
    Parts
    -0.56
     Tasmania
    -0.55
     Bureau
    -0.54
     rubbish
    -0.54
    Status
    -0.54
     Profile
    -0.54
    POSITIVE LOGITS
    £ı
    0.69
    thur
    0.67
    isode
    0.64
    vine
    0.64
    emonic
    0.64
    tro
    0.63
    xon
    0.63
     pains
    0.62
     snowball
    0.57
     pigeon
    0.57
    Act Density 0.652%

    No Known Activations