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

    Neuronpedia

    INDEX
    Explanations

    copyright statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to copyright and publishing restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mazda
    -0.57
    lication
    -0.55
     Mant
    -0.54
     Pok
    -0.54
     testament
    -0.53
    VIDIA
    -0.53
     Hir
    -0.51
     Sabb
    -0.51
    oplan
    -0.51
     attraction
    -0.51
    POSITIVE LOGITS
     reprint
    0.79
     reproduced
    0.76
     sourced
    0.69
     redistributed
    0.66
    vana
    0.66
    edited
    0.66
     reproduce
    0.65
    ahl
    0.64
    ashington
    0.62
    published
    0.62
    Act Density 0.031%

    No Known Activations