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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action and making decisions

    oai_token-act-pair · gpt-3.5-turbo

    imperative verbs indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Levant
    -0.70
    ELD
    -0.66
    DERR
    -0.64
    Pain
    -0.62
     Slug
    -0.61
    MpServer
    -0.58
    Usage
    -0.57
     penned
    -0.57
     triggered
    -0.57
     irritating
    -0.56
    POSITIVE LOGITS
     ourselves
    1.20
     celebrate
    0.87
     presume
    0.83
     educate
    0.81
     collectively
    0.81
    egu
    0.81
     conclude
    0.80
     revisit
    0.79
    igmat
    0.78
     simplify
    0.78
    Act Density 0.223%

    No Known Activations