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

    Neuronpedia

    INDEX
    Explanations

    expressions of dislike or frustration towards jobs, styles, and social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressing hate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.53
    IsMutable
    -0.51
    InstrumentedTest
    -0.45
     kurtka
    -0.44
     profitably
    -0.44
    SaveChangesAsync
    -0.44
     $_"
    -0.43
    verständlich
    -0.43
    RTEX
    -0.42
     Qaraldi
    -0.41
    POSITIVE LOGITS
     hated
    0.68
     HATE
    0.62
     hates
    0.61
     hate
    0.60
     dislike
    0.59
     disliked
    0.58
     unhappy
    0.53
     unpleasant
    0.50
     worst
    0.50
     annoying
    0.50
    Act Density 0.021%

    No Known Activations