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

    Neuronpedia

    INDEX
    Explanations

    personal interaction and dialogue between individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iba
    -0.83
    uffle
    -0.75
    ater
    -0.71
    CHA
    -0.66
    asha
    -0.65
    aten
    -0.64
    aters
    -0.64
    gra
    -0.63
     offend
    -0.62
    taboola
    -0.61
    POSITIVE LOGITS
     thumbs
    0.91
     opportunity
    0.89
     chance
    0.88
     permission
    0.81
     choice
    0.78
     priority
    0.77
     pointers
    0.77
     pause
    0.76
     assurances
    0.76
     berth
    0.74
    Act Density 0.975%

    No Known Activations