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

    Neuronpedia

    INDEX
    Explanations

    references to APIs and functions related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -1.51
    himself
    -1.11
     Himself
    -1.08
     koji
    -0.92
     który
    -0.88
     који
    -0.85
     který
    -0.85
     який
    -0.84
     который
    -0.84
     ktorý
    -0.84
    POSITIVE LOGITS
     herself
    1.11
     she
    0.97
    she
    0.73
    herself
    0.67
    She
    0.63
     She
    0.60
    她
    0.59
     αυτή
    0.54
     która
    0.52
     그녀
    0.52
    Act Density 0.178%

    No Known Activations