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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the topic or main focus of a discussion or piece of content

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "subject" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERROR
    -0.70
    ATIONAL
    -0.69
    IELD
    -0.68
     Zimmer
    -0.65
    ECK
    -0.65
    BLIC
    -0.65
    zza
    -0.64
    OURCE
    -0.63
    FLAG
    -0.62
    estern
    -0.61
    POSITIVE LOGITS
    ivity
    0.95
    matter
    0.92
    ively
    0.86
    itatively
    0.83
    classes
    0.81
     prosec
    0.80
     Subjects
    0.80
    ically
    0.80
    ifies
    0.78
    ivist
    0.77
    Act Density 0.014%

    No Known Activations