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

    Neuronpedia

    INDEX
    Explanations

    references to fictional settings and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undos
    -0.15
    eor
    -0.15
    zone
    -0.14
     Pew
    -0.14
    adel
    -0.14
     shield
    -0.14
    ¦¬
    -0.14
     zone
    -0.14
    agner
    -0.14
    antas
    -0.14
    POSITIVE LOGITS
    /bower
    0.17
    aro
    0.16
     unspecified
    0.15
    ignon
    0.15
     post
    0.15
    post
    0.15
     prere
    0.15
    beros
    0.15
     fict
    0.15
     θÎŃ
    0.14
    Act Density 0.111%

    No Known Activations