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

    Neuronpedia

    INDEX
    Explanations

    words related to enabling or permitting actions or functionalities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the concept of enabling or permitting actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worn
    -0.62
    boy
    -0.62
    ko
    -0.62
    bell
    -0.61
    been
    -0.60
    ta
    -0.59
    dom
    -0.59
    buster
    -0.59
    kind
    -0.56
    bage
    -0.55
    POSITIVE LOGITS
     us
    1.03
     users
    1.02
    awaru
    0.90
    hift
    0.81
     buyers
    0.81
     passers
    0.81
    Reviewer
    0.80
     developers
    0.80
     programmers
    0.78
     seamless
    0.77
    Act Density 0.100%

    No Known Activations