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

    Neuronpedia

    INDEX
    Explanations

    colors and physical objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various colors, social issues, and emotional concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.61
    antha
    -0.60
    adobe
    -0.60
    Legend
    -0.59
    Ni
    -0.59
    AAA
    -0.58
    ©¶æ
    -0.57
    isu
    -0.56
    OSP
    -0.56
    redited
    -0.55
    POSITIVE LOGITS
     alike
    2.05
     respectively
    1.76
     separately
    0.97
     interchange
    0.97
     together
    0.93
     combo
    0.91
     simultaneously
    0.87
     versa
    0.86
     etc
    0.84
     combinations
    0.84
    Act Density 0.462%

    No Known Activations