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

    Neuronpedia

    INDEX
    Explanations

    references to the Vatican and its properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arness
    -0.15
    clr
    -0.14
    uset
    -0.14
    .undo
    -0.14
     Vend
    -0.14
    outil
    -0.14
    ouce
    -0.14
    uttle
    -0.14
    arah
    -0.14
    kou
    -0.14
    POSITIVE LOGITS
    ijd
    0.26
    ussen
    0.26
    ij
    0.25
    ien
    0.24
    egen
    0.23
    ota
    0.23
    eken
    0.22
    eg
    0.21
    ient
    0.20
    ucht
    0.20
    Act Density 0.007%

    No Known Activations