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

    Neuronpedia

    INDEX
    Explanations

    diverse types or categories of things

    oai_token-act-pair · gpt-3.5-turbo

    references to varieties or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LAN
    -0.81
    arching
    -0.72
    adium
    -0.71
    LESS
    -0.68
    ked
    -0.68
    DS
    -0.66
    board
    -0.65
    stood
    -0.64
    eka
    -0.64
    boa
    -0.63
    POSITIVE LOGITS
     sorts
    1.12
    ãĤ¦ãĤ¹
    0.89
     kinds
    0.85
     explan
    0.83
     sort
    0.82
    sort
    0.81
     mosqu
    0.80
    Sort
    0.79
    ername
    0.76
    é¾įåĸļ士
    0.75
    Act Density 0.004%

    No Known Activations