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

    Neuronpedia

    INDEX
    Explanations

    official statements or memos issued by authorities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to official statements or communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anism
    -0.85
    onge
    -0.79
    cells
    -0.77
    aten
    -0.71
    lords
    -0.69
    acy
    -0.69
    casts
    -0.67
     friendships
    -0.66
    caps
    -0.64
    ateurs
    -0.63
    POSITIVE LOGITS
     scathing
    1.09
     whopping
    1.06
     lengthy
    1.04
     slew
    1.03
     memorandum
    1.02
     lot
    1.02
     preliminary
    1.00
     bombshell
    0.99
     flurry
    0.99
     plea
    0.96
    Act Density 0.304%

    No Known Activations