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

    Neuronpedia

    INDEX
    Explanations

    keywords related to common or essential items or things

    oai_token-act-pair · gpt-3.5-turbo

    terms related to staple foods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.87
    hani
    -0.82
    hap
    -0.81
    odore
    -0.79
    irlf
    -0.76
    hid
    -0.75
    oping
    -0.73
    ammers
    -0.73
    apego
    -0.71
    atti
    -0.70
    POSITIVE LOGITS
     staple
    1.22
     staples
    1.20
    ãĤ´
    0.83
    stay
    0.74
    ãĤ¢ãĥ«
    0.74
    ãĥ¢
    0.73
    weights
    0.72
    fields
    0.70
    é¾įå¥ij士
    0.69
    ãĥ¯ãĥ³
    0.68
    Act Density 0.007%

    No Known Activations