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

    Neuronpedia

    INDEX
    Explanations

    mentions of rumors or speculation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rumor"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artney
    -0.73
    DOS
    -0.73
    ĸļ
    -0.72
    alone
    -0.71
    acted
    -0.70
    hematic
    -0.69
    nea
    -0.69
    itar
    -0.69
    instance
    -0.69
    mand
    -0.68
    POSITIVE LOGITS
     rumors
    1.12
     rumor
    1.09
     rumours
    1.03
    Rum
    0.87
     gossip
    0.86
     cov
    0.83
     speculate
    0.82
     speculation
    0.81
     indu
    0.80
     leak
    0.79
    Act Density 0.048%

    No Known Activations