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

    Neuronpedia

    INDEX
    Explanations

    verbs related to expelling or emitting forcefully

    oai_token-act-pair · gpt-3.5-turbo

    words related to the act of spreading or expressing information, often in a negative or overwhelming sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĸ
    -0.79
    iatus
    -0.70
    abet
    -0.70
    brance
    -0.70
    teness
    -0.69
     Skydragon
    -0.67
    ession
    -0.66
    externalActionCode
    -0.65
    occup
    -0.65
     photograp
    -0.64
    POSITIVE LOGITS
     forth
    1.17
     havoc
    1.14
     vitri
    0.98
     insults
    0.90
     scorn
    0.89
     praise
    0.89
     apologies
    0.88
     nonsense
    0.88
     venom
    0.87
     slogans
    0.87
    Act Density 0.151%

    No Known Activations