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

    Neuronpedia

    INDEX
    Explanations

    instances where something is not just one thing but also something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.88
    ues
    -0.70
     Hanson
    -0.68
     Nanto
    -0.67
    ij士
    -0.66
    Īè
    -0.66
    ³
    -0.64
     Rohing
    -0.62
    vir
    -0.60
    00200000
    -0.59
    POSITIVE LOGITS
    oped
    0.69
    tem
    0.67
    schild
    0.63
     physically
    0.62
     obe
    0.61
    onne
    0.61
     professionally
    0.60
    usalem
    0.58
     financially
    0.58
    akia
    0.58
    Act Density 0.026%

    No Known Activations