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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing similarity or commonality

    oai_token-act-pair · gpt-3.5-turbo

    the concept of similarity or commonality among different groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohyd
    -0.71
    erenn
    -0.70
    stra
    -0.65
    Frag
    -0.64
    someone
    -0.57
    Sem
    -0.56
    Ther
    -0.55
    give
    -0.55
    0002
    -0.55
    por
    -0.55
    POSITIVE LOGITS
     alike
    1.22
    soever
    1.02
     sexes
    0.84
    sheets
    0.79
    wcs
    0.77
    lihood
    0.75
    !--
    0.74
    ãĤ¼ãĤ¦ãĤ¹
    0.70
     auditor
    0.70
    peak
    0.70
    Act Density 0.006%

    No Known Activations