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

    Neuronpedia

    INDEX
    Explanations

    words related to legal documents or official programs

    oai_token-act-pair · gpt-3.5-turbo

    the word "deliver" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     buckle
    -0.59
     dece
    -0.59
    manship
    -0.58
    andals
    -0.57
    pai
    -0.55
     Drain
    -0.55
     Sapphire
    -0.55
    iege
    -0.54
    Downloadha
    -0.54
     Chef
    -0.54
    POSITIVE LOGITS
    ãĤ¡
    0.96
    iver
    0.89
    glass
    0.89
    ãĤ©
    0.84
    loo
    0.83
    ativity
    0.79
    mingham
    0.78
    ELY
    0.77
    gence
    0.75
    atives
    0.74
    Act Density 0.036%

    No Known Activations