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

    Neuronpedia

    INDEX
    Explanations

    the name "Evans" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    the name "Evans" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MY
    -0.71
    PM
    -0.71
     spare
    -0.70
    ppo
    -0.68
    yright
    -0.65
    gio
    -0.64
     vengeance
    -0.63
     deaf
    -0.63
    iliated
    -0.63
    cial
    -0.62
    POSITIVE LOGITS
     Evans
    1.01
    ville
    0.89
    burgh
    0.83
    olution
    0.80
     Davies
    0.79
    hoe
    0.78
    olate
    0.77
    loo
    0.77
    olver
    0.77
    dale
    0.76
    Act Density 0.003%

    No Known Activations