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

    Neuronpedia

    INDEX
    Explanations

    phrases related to granting permission or approval

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to permission or approval, particularly using the term "green light."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -1.12
    ngth
    -0.80
    icum
    -0.73
    sylv
    -0.72
     resil
    -0.72
    myra
    -0.70
    ulz
    -0.70
    incial
    -0.69
    hran
    -0.69
    oln
    -0.69
    POSITIVE LOGITS
    edly
    0.89
    ibility
    0.80
    ed
    0.80
    lights
    0.78
    aneously
    0.76
    oned
    0.75
    WAY
    0.73
    ISA
    0.73
    way
    0.72
     waivers
    0.70
    Act Density 0.053%

    No Known Activations