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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions and responsibilities related to humanitarian issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĸ
    -0.67
     burner
    -0.65
    Cooldown
    -0.59
     hy
    -0.57
     territ
    -0.54
    detail
    -0.54
     Dek
    -0.53
    gradient
    -0.53
    /-
    -0.53
    ODY
    -0.51
    POSITIVE LOGITS
     sue
    0.65
     join
    0.64
    who
    0.63
     decide
    0.62
    unctions
    0.60
     participate
    0.59
    quez
    0.59
    elsen
    0.59
    imei
    0.58
     scrambling
    0.58
    Act Density 0.463%

    No Known Activations