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

    Neuronpedia

    INDEX
    Explanations

    religious terms and social dynamics related to conflict and hierarchy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    forestation
    -0.65
     unbeliev
    -0.62
    osphere
    -0.60
     impunity
    -0.59
    osi
    -0.59
     insanity
    -0.58
     vacancy
    -0.58
    ãĥį
    -0.57
     Sense
    -0.57
    asus
    -0.56
    POSITIVE LOGITS
     themselves
    1.12
    hips
    1.08
    mith
    1.08
     unto
    0.96
    hip
    0.95
    pring
    0.90
    ometimes
    0.85
    cale
    0.85
    cript
    0.84
     ourselves
    0.83
    Act Density 0.282%

    No Known Activations