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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific goals or objectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intentions or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.75
    wine
    -0.65
    mson
    -0.65
    bush
    -0.65
    condition
    -0.65
    minus
    -0.64
    hours
    -0.64
    orce
    -0.63
    involved
    -0.63
    imore
    -0.63
    POSITIVE LOGITS
    -+-+
    0.71
     overturn
    0.67
     topp
    0.66
     perfection
    0.65
    ãĥĦ
    0.65
     apprehend
    0.65
     achieving
    0.64
     inflicting
    0.64
     accompl
    0.64
    ä½ľ
    0.63
    Act Density 0.326%

    No Known Activations