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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     aussitôt
    -0.92
     quelquefois
    -0.87
     soudain
    -0.85
     poichè
    -0.85
     perciò
    -0.85
     quoique
    -0.84
     volon
    -0.83
    Ikr
    -0.83
     constamment
    -0.83
     librement
    -0.81
    POSITIVE LOGITS
    YOND
    0.59
     also
    0.52
    wavering
    0.52
     MainAxisSize
    0.49
    olybden
    0.49
    ISTRATION
    0.49
     importantly
    0.48
     함께
    0.48
    amp
    0.47
    thora
    0.47
    Act Density 0.125%

    No Known Activations