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

    Neuronpedia

    INDEX
    Explanations

    terms related to defaults and definitions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to definitions and defaults in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.64
    raped
    -0.61
    pring
    -0.61
     heavens
    -0.59
     glim
    -0.58
     Vic
    -0.58
    wait
    -0.57
     Vinyl
    -0.57
    istant
    -0.57
    sole
    -0.56
    POSITIVE LOGITS
    aws
    0.72
    ghan
    0.71
    tera
    0.70
     Belg
    0.69
    VERTISEMENT
    0.68
    esm
    0.67
    wik
    0.65
    tesy
    0.63
    reau
    0.63
    ©¶æ¥µ
    0.61
    Act Density 0.035%

    No Known Activations