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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rumors and reports

    oai_token-act-pair · gpt-3.5-turbo

    statements related to rumors and unconfirmed reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.03
    aho
    -0.88
    alone
    -0.84
    anchester
    -0.82
    gaard
    -0.79
    ignt
    -0.79
    uristic
    -0.78
    alez
    -0.77
    galitarian
    -0.77
    undrum
    -0.75
    POSITIVE LOGITS
     rumours
    0.93
     impending
    0.89
     rumor
    0.85
     Rum
    0.85
     rumors
    0.84
     sightings
    0.84
     assass
    0.74
     leaks
    0.71
     rum
    0.71
    rum
    0.70
    Act Density 0.341%

    No Known Activations