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

    Neuronpedia

    INDEX
    Explanations

    references to commonality and shared experiences or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shack
    -0.18
    ged
    -0.15
    idel
    -0.15
    ứ
    -0.14
    gio
    -0.14
    ges
    -0.14
    moz
    -0.14
    ats
    -0.14
    oras
    -0.14
    ainless
    -0.14
    POSITIVE LOGITS
    wealth
    0.51
    ality
    0.36
     denominator
    0.34
     sense
    0.28
    sense
    0.28
    place
    0.24
    alty
    0.24
    places
    0.23
    alties
    0.23
     Sense
    0.23
    Act Density 0.031%

    No Known Activations