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

    Neuronpedia

    INDEX
    Explanations

    references to age and maturity in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stery
    -0.15
     tend
    -0.15
    atform
    -0.15
    idir
    -0.15
     neither
    -0.15
    almost
    -0.14
    brace
    -0.14
     nobody
    -0.14
     no
    -0.14
     tended
    -0.14
    POSITIVE LOGITS
     ever
    0.32
     EVER
    0.29
     anywhere
    0.28
     necessarily
    0.28
     anything
    0.27
     any
    0.25
     somehow
    0.24
    anything
    0.24
     suddenly
    0.23
    æľīä»Ģä¹Ī
    0.22
    Act Density 0.212%

    No Known Activations