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

    Neuronpedia

    INDEX
    Explanations

    references to adversaries or enemies in a context involving conflict or competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lothar
    -0.70
    ledad
    -0.63
     utafitiHapana
    -0.61
     Norr
    -0.60
    wollen
    -0.58
    exclusion
    -0.58
    axx
    -0.58
    insatz
    -0.56
     usati
    -0.56
    ouille
    -0.56
    POSITIVE LOGITS
     Maturity
    1.05
     maturity
    1.03
     Mentor
    0.99
     mature
    0.97
     Mature
    0.95
     Securities
    0.92
    maturity
    0.91
     securities
    0.91
    Mature
    0.89
     mentor
    0.88
    Act Density 0.052%

    No Known Activations