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

    Neuronpedia

    INDEX
    Explanations

    mixtures or combinations of different elements

    oai_token-act-pair · gpt-3.5-turbo

    references to mixtures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.95
    orth
    -0.75
    ond
    -0.73
     Passage
    -0.72
     Borders
    -0.71
    £
    -0.69
    ighth
    -0.69
    yright
    -0.69
    ¥ŀ
    -0.67
    stra
    -0.67
    POSITIVE LOGITS
     mixture
    1.18
     mixes
    1.03
     blends
    0.96
     mix
    0.95
     conco
    0.89
     blend
    0.87
     blending
    0.79
     amalg
    0.77
     mixing
    0.76
    ichick
    0.75
    Act Density 0.012%

    No Known Activations