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

    Neuronpedia

    INDEX
    Explanations

    words related to non-conformity and challenging traditional structures

    oai_token-act-pair · gpt-3.5-turbo

    references to different forms of artistic expression or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brow
    -0.66
     paras
    -0.64
     [+
    -0.61
     simmer
    -0.60
     Lan
    -0.59
     Regional
    -0.59
     si
    -0.58
     breath
    -0.58
     Breath
    -0.57
     Seas
    -0.56
    POSITIVE LOGITS
    idable
    1.25
    atted
    1.07
    aldehyde
    1.07
    ulations
    0.97
    ative
    0.95
    ula
    0.89
    ations
    0.88
    ational
    0.88
    achu
    0.88
    ulum
    0.87
    Act Density 0.011%

    No Known Activations