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

    Neuronpedia

    INDEX
    Explanations

    long strings of characters marked by symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of the tilde symbol (~)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dynamics
    -0.82
     Luther
    -0.72
     Jinn
    -0.72
    iasis
    -0.66
     Bulgar
    -0.65
     implant
    -0.65
     bearer
    -0.65
     photoc
    -0.64
     modification
    -0.64
    iant
    -0.63
    POSITIVE LOGITS
    =~=~
    1.40
    #$
    1.00
    ãģ¦
    0.83
    sil
    0.83
    GW
    0.81
    ã
    0.81
    LI
    0.80
    _-
    0.79
    rules
    0.78
    $
    0.77
    Act Density 0.023%

    No Known Activations