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

    Neuronpedia

    INDEX
    Explanations

    special characters separating strings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the tilde symbol (~)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dynamics
    -0.78
    iant
    -0.74
     Luther
    -0.71
    inals
    -0.67
     implant
    -0.67
    iasis
    -0.67
     Jinn
    -0.66
    uments
    -0.65
    aceous
    -0.65
     bearer
    -0.64
    POSITIVE LOGITS
    =~=~
    1.30
    #$
    1.02
    ãģ¦
    0.96
     ~
    0.80
    ã
    0.79
    GW
    0.79
    {{
    0.73
    NY
    0.73
    _>
    0.72
    OOL
    0.72
    Act Density 0.019%

    No Known Activations