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

    Neuronpedia

    INDEX
    Explanations

    negative emotions and resentful sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.84
    ValueStyle
    -0.62
     snippetHide
    -0.60
    Datuak
    -0.58
     surla
    -0.57
    -0.53
    ModelAdmin
    -0.53
    bootstrapcdn
    -0.52
    AddTagHelper
    -0.51
     nakalista
    -0.50
    POSITIVE LOGITS
     hate
    1.01
     hatred
    1.01
     hates
    0.93
     hating
    0.93
     Hate
    0.86
    hate
    0.84
     HATE
    0.83
     hated
    0.82
    Hate
    0.77
     ненави
    0.76
    Act Density 0.265%

    No Known Activations