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

    Neuronpedia

    INDEX
    Explanations

    mixtures created by combining different ingredients or components

    oai_token-act-pair · gpt-3.5-turbo

    references to mixtures or combinations of ingredients or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.94
    £
    -0.78
    stra
    -0.77
    orth
    -0.75
    ighth
    -0.72
    ¥ŀ
    -0.72
     Passage
    -0.71
    ond
    -0.68
     Borders
    -0.67
    yright
    -0.67
    POSITIVE LOGITS
     mixture
    1.16
     blends
    0.95
     conco
    0.93
     blend
    0.89
     mixes
    0.88
     mix
    0.84
     Flavoring
    0.83
     blending
    0.76
     mixed
    0.74
     thereof
    0.74
    Act Density 0.016%

    No Known Activations