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

    Neuronpedia

    INDEX
    Explanations

    phrases related to open access content and fonts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    _-
    -0.77
    agher
    -0.72
    kh
    -0.70
    bowl
    -0.69
     Kear
    -0.66
    kas
    -0.66
    akuya
    -0.64
    =-=-=-=-=-=-=-=-
    -0.64
    eah
    -0.64
    asley
    -0.63
    POSITIVE LOGITS
     backdoor
    0.74
     doors
    0.71
     Pandora
    0.68
     airspace
    0.68
     Doors
    0.67
     portal
    0.66
     doctrine
    0.65
    esame
    0.65
     welcome
    0.65
     door
    0.64
    Act Density 0.089%

    No Known Activations