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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs that indicate likelihood or potential action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate likelihood or probability of various outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    limits
    -0.74
    comings
    -0.70
    padding
    -0.69
    minus
    -0.68
    Loading
    -0.68
    soDeliveryDate
    -0.67
    roads
    -0.67
    ä¹ĭ
    -0.66
    flying
    -0.65
    feeding
    -0.65
    POSITIVE LOGITS
     succeed
    1.18
     offend
    1.14
     receive
    1.14
     commit
    1.12
     be
    1.12
     participate
    1.12
     engage
    1.11
     perceive
    1.11
     survive
    1.09
     cooperate
    1.09
    Act Density 0.074%

    No Known Activations