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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and organizations as well as specific dates

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly names and social media handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CP
    -1.28
     CP
    -1.07
     CPS
    -1.05
     CK
    -1.05
    CC
    -1.02
     Cav
    -1.01
    ACP
    -1.01
     CB
    -0.98
    PC
    -0.96
    CB
    -0.96
    POSITIVE LOGITS
    REE
    0.91
     Reed
    0.84
     elf
    0.84
    rees
    0.77
     rall
    0.77
     Weir
    0.76
    rift
    0.75
    eri
    0.74
    RL
    0.73
    lde
    0.73
    Act Density 1.027%

    No Known Activations