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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing idiomatic expressions involving physical actions and reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions that describe criticism or negative judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.94
    xual
    -0.70
    fts
    -0.69
    alg
    -0.66
    AUD
    -0.63
     RELE
    -0.62
    aren
    -0.62
    ouver
    -0.61
    iferation
    -0.61
    qus
    -0.60
    POSITIVE LOGITS
     os
    0.68
     coffin
    0.67
     bucket
    0.63
    osa
    0.60
     ozone
    0.57
     forehead
    0.57
    Thor
    0.56
     shoulder
    0.56
     paradise
    0.55
     sore
    0.55
    Act Density 0.138%

    No Known Activations