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

    Neuronpedia

    INDEX
    Explanations

    phrases related to risk, strategy, and health issues

    oai_token-act-pair · gpt-3.5-turbo

    elements related to specific actions and the presence of various risks or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.86
    older
    -0.74
    ochet
    -0.72
    peria
    -0.69
     strut
    -0.66
    ortium
    -0.65
     Dodge
    -0.64
    heet
    -0.64
    htar
    -0.63
    heed
    -0.60
    POSITIVE LOGITS
    ivities
    1.09
     ones
    1.09
    asses
    1.05
    keys
    1.04
     items
    1.02
    mails
    1.01
    ables
    1.00
     races
    0.99
    isons
    0.99
     lands
    0.99
    Act Density 0.539%

    No Known Activations