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

    Neuronpedia

    INDEX
    Explanations

    words related to acceptance and agreement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     glands
    -0.71
    ixt
    -0.70
    ionage
    -0.70
    vertisement
    -0.69
    ibur
    -0.69
    borough
    -0.67
     Indust
    -0.65
    igil
    -0.65
    iferation
    -0.65
    borgh
    -0.64
    POSITIVE LOGITS
    ably
    0.90
    ances
    0.85
     accepting
    0.84
     acceptance
    0.83
     responsibility
    0.81
    ANCE
    0.78
     uncond
    0.78
    enance
    0.77
     bribes
    0.75
     accept
    0.75
    Act Density 0.670%

    No Known Activations