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

    Neuronpedia

    INDEX
    Explanations

    adjectives that indicate strong negative emotions or severe conditions

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

    negative intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.59
    +#+
    -0.57
    HomeAsUpEnabled
    -0.54
     pleaſure
    -0.54
    SharedDtor
    -0.53
    -0.53
     springfox
    -0.51
     defaultstate
    -0.50
    richTextPanel
    -0.50
     nakalista
    -0.49
    POSITIVE LOGITS
     bad
    0.73
     terribly
    0.71
     horribly
    0.66
     сильно
    0.65
     severe
    0.63
    bad
    0.62
     terrible
    0.60
     badly
    0.60
     mocno
    0.59
    Bad
    0.57
    Act Density 0.021%

    No Known Activations