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

    Neuronpedia

    INDEX
    Explanations

    reports and rumors about various topics or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of reports and assertions about events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izont
    -0.85
    ãĤ´ãĥ³
    -0.81
    ĸļ
    -0.81
    aho
    -0.78
    wow
    -0.77
    gur
    -0.76
    ãĤ¤ãĥĪ
    -0.74
    akable
    -0.74
    ield
    -0.74
    apsed
    -0.71
    POSITIVE LOGITS
     eyewitness
    0.76
     spies
    0.74
     Lans
    0.72
     Rum
    0.72
     rumor
    0.71
     CIA
    0.71
     rumors
    0.71
     Apostle
    0.70
     bribes
    0.69
     DF
    0.68
    Act Density 0.268%

    No Known Activations