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

    Neuronpedia

    INDEX
    Explanations

    words related to false beliefs or misconceptions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with false beliefs and misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.85
    gre
    -0.71
    zens
    -0.64
    single
    -0.64
    ossus
    -0.62
    enum
    -0.61
    entin
    -0.60
    amen
    -0.60
    izont
    -0.59
    intern
    -0.58
    POSITIVE LOGITS
     regarding
    1.24
     about
    1.22
     concerning
    1.21
    mith
    1.09
     ABOUT
    1.04
     pertaining
    0.98
     uttered
    0.94
    uggest
    0.92
     relating
    0.91
     About
    0.88
    Act Density 0.245%

    No Known Activations