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

    Neuronpedia

    INDEX
    Explanations

    online forums or discussion threads

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     gend
    -0.55
     zyn
    -0.52
     kram
    -0.52
     Gez
    -0.50
     gesta
    -0.49
     krab
    -0.48
     wein
    -0.47
     glan
    -0.47
    Pá
    -0.47
     petra
    -0.47
    POSITIVE LOGITS
     forum
    1.35
     Forum
    1.25
     forums
    1.21
    Forum
    1.20
    forum
    1.19
     Forums
    1.13
     FORUM
    1.01
    FORUM
    0.99
    Forums
    0.89
    forums
    0.84
    Act Density 0.101%

    No Known Activations