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

    Neuronpedia

    INDEX
    Explanations

    actions to perform

    oai_token-act-pair · gpt-3.5-turbo

    commands or instructions involving the action of pressing buttons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cloak
    -0.68
     Equality
    -0.68
    BuyableInstoreAndOnline
    -0.66
     Trayvon
    -0.65
     Elves
    -0.64
     Emin
    -0.64
     Asgard
    -0.64
    beard
    -0.63
     Druid
    -0.63
     [|
    -0.62
    POSITIVE LOGITS
    urized
    1.34
    ature
    0.96
    ariat
    0.87
    atures
    0.84
    aic
    0.81
    press
    0.81
    ures
    0.81
    roth
    0.80
    ur
    0.77
    ername
    0.76
    Act Density 0.025%

    No Known Activations