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

    Neuronpedia

    INDEX
    Explanations

    terms related to desirability and the opposite concept of undesirability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensing
    -0.15
    лÑİб
    -0.15
    ulin
    -0.15
     verr
    -0.15
    usal
    -0.15
    æ¹¾
    -0.15
    enthal
    -0.14
    essler
    -0.14
    ivia
    -0.14
     pé
    -0.14
    POSITIVE LOGITS
    gart
    0.14
    WidgetItem
    0.14
    memberof
    0.14
    _partner
    0.14
    054
    0.14
    .rem
    0.14
     Partner
    0.14
     åī
    0.13
    Silver
    0.13
    489
    0.13
    Act Density 0.007%

    No Known Activations