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

    Neuronpedia

    INDEX
    Explanations

    parts of the text related to meanings of words or terms

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to meaning and understanding within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    helial
    -0.63
    odge
    -0.56
    akia
    -0.56
    oak
    -0.56
    enture
    -0.55
     redes
    -0.55
    riched
    -0.55
    asma
    -0.55
    ranging
    -0.54
    ielding
    -0.52
    POSITIVE LOGITS
     thereof
    1.33
     of
    1.23
     Of
    1.03
    Of
    1.03
     OF
    0.98
    of
    0.91
     itself
    0.84
    iest
    0.82
    liest
    0.78
    âĢ
    0.76
    Act Density 0.621%

    No Known Activations