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

    Neuronpedia

    INDEX
    Explanations

    instances where something is declared as permissible or free from blame or suspicion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cleared" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENTS
    -0.75
    ENT
    -0.75
    egal
    -0.74
    ENC
    -0.70
    INA
    -0.67
    lav
    -0.64
    ADD
    -0.63
    EG
    -0.61
    ingo
    -0.61
    DOM
    -0.61
    POSITIVE LOGITS
     clears
    1.01
     cleared
    0.93
     waivers
    0.89
    20439
    0.79
    houses
    0.78
     paperwork
    0.76
    ĵĺ
    0.74
     clearance
    0.74
    sheets
    0.74
     Clear
    0.73
    Act Density 0.015%

    No Known Activations