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

    Neuronpedia

    INDEX
    Explanations

    references to males or pronouns specifically associated with men

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.83
     intrusion
    -0.71
    DAY
    -0.61
     Solitaire
    -0.60
     reinforcement
    -0.59
     withdrawal
    -0.59
    BALL
    -0.58
     cred
    -0.56
    INGTON
    -0.56
     gems
    -0.55
    POSITIVE LOGITS
    gemony
    1.19
    resy
    1.18
    arer
    1.15
    lder
    1.13
    isen
    1.05
    arers
    1.05
    ALTH
    1.03
    uristic
    1.03
    cht
    1.01
    idel
    1.01
    Act Density 0.031%

    No Known Activations