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

    Neuronpedia

    INDEX
    Explanations

    phrases describing conflict or violence

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

    Adjectives describing emotional states

    np_acts-logits-general · gemini-2.0-flash

    states of being or reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.77
     Jefus
    -0.73
    HtmlAttribute
    -0.73
    Hentet
    -0.68
     himſelf
    -0.68
     itſelf
    -0.67
     themſelves
    -0.67
     Monfieur
    -0.66
     pleaſure
    -0.64
    StoryboardSegue
    -0.64
    POSITIVE LOGITS
     eager
    1.05
     shocked
    1.04
     stunned
    1.04
     frustrated
    1.04
     tired
    1.00
     reluctant
    0.97
     unwilling
    0.96
     bewildered
    0.95
     anxious
    0.95
     terrified
    0.95
    Act Density 0.243%

    No Known Activations