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

    Neuronpedia

    INDEX
    Explanations

    numeric references to weeks or groups within a series or competition

    oai_token-act-pair · gpt-3.5-turbo

    references to specific weeks and groups in a scheduling context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckland
    -0.88
    issance
    -0.84
    soever
    -0.76
    ersen
    -0.68
    PLIED
    -0.68
    esome
    -0.67
    ntil
    -0.66
    glomer
    -0.65
    est
    -0.64
    esthetic
    -0.63
    POSITIVE LOGITS
     Maker
    0.73
    Maker
    0.71
     orders
    0.67
     IV
    0.65
     Viet
    0.63
    Lv
    0.62
     Vega
    0.62
     1
    0.61
     XXX
    0.61
     Zero
    0.60
    Act Density 0.250%

    No Known Activations