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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with social interactions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cket
    -0.16
    öl
    -0.16
     Tradition
    -0.15
    .nom
    -0.15
    ih
    -0.14
    ör
    -0.14
    erner
    -0.14
    alled
    -0.13
    onne
    -0.13
     loyal
    -0.13
    POSITIVE LOGITS
     there
    0.16
    .jquery
    0.15
    æŃ£åľ¨
    0.14
    onth
    0.13
    ãĥ¼ãĥĵ
    0.13
    htable
    0.13
     workings
    0.13
    OURCES
    0.13
    enegro
    0.13
    eyen
    0.13
    Act Density 0.007%

    No Known Activations