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

    Neuronpedia

    INDEX
    Explanations

    sentences related to political and legal matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     varies
    -0.68
     preserves
    -0.66
     vary
    -0.65
     someday
    -0.65
    vec
    -0.64
     meshes
    -0.64
     theorem
    -0.64
     afterlife
    -0.64
     backgrounds
    -0.63
     nowadays
    -0.62
    POSITIVE LOGITS
    lished
    0.86
     announcing
    0.84
     celebrated
    0.80
     headlined
    0.76
    iphany
    0.74
     rumors
    0.71
     earthqu
    0.70
    when
    0.69
    Reviewer
    0.68
     announced
    0.68
    Act Density 6.137%

    No Known Activations