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

    Neuronpedia

    INDEX
    Explanations

    keywords related to queries or questions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "When."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.67
    atic
    -0.66
    åĤ
    -0.64
    kaya
    -0.63
    harm
    -0.63
    medi
    -0.61
    aido
    -0.61
    ymph
    -0.60
    alian
    -0.58
    alle
    -0.58
    POSITIVE LOGITS
    soever
    1.37
     asked
    0.87
     confronted
    0.86
    irlf
    0.83
     pressed
    0.78
     faced
    0.76
    quickShipAvailable
    0.74
    bestos
    0.73
     contacted
    0.72
    theless
    0.72
    Act Density 0.079%

    No Known Activations