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

    Neuronpedia

    INDEX
    Explanations

    phrases related to misinformation and misrepresentation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to misinformation and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.81
    enne
    -0.79
    aris
    -0.79
    eatures
    -0.76
    ftime
    -0.76
    illin
    -0.75
    ppa
    -0.74
    olis
    -0.73
    agos
    -0.73
     Pulse
    -0.72
    POSITIVE LOGITS
     inaccurate
    1.30
     inadequ
    1.29
     inaccur
    1.28
     ineffective
    1.27
     erroneous
    1.26
     misrepresent
    1.24
     inacc
    1.24
     misunderstood
    1.24
     unworthy
    1.23
     unreliable
    1.22
    Act Density 0.528%

    No Known Activations