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

    Neuronpedia

    INDEX
    Explanations

    statements of personal experience or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.19
    ione
    -0.15
     themselves
    -0.14
    lain
    -0.14
    erva
    -0.13
    vanished
    -0.13
    æľīä»Ģä¹Ī
    -0.13
    lung
    -0.13
    me
    -0.13
    s
    -0.13
    POSITIVE LOGITS
     heard
    0.22
     never
    0.22
     always
    0.21
     fond
    0.20
     known
    0.20
     loved
    0.20
     often
    0.20
     no
    0.20
     rarely
    0.20
     noticed
    0.20
    Act Density 0.189%

    No Known Activations