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

    Neuronpedia

    INDEX
    Explanations

    expressions of return or revisiting actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ColumnHeader
    -0.17
    ertest
    -0.16
    unting
    -0.16
    $_['
    -0.15
    raki
    -0.15
    ntax
    -0.15
    inded
    -0.14
    bjerg
    -0.14
    ç¤
    -0.14
    oden
    -0.14
    POSITIVE LOGITS
    ãĤħ
    0.17
     later
    0.16
    ibr
    0.16
     chir
    0.15
     h
    0.15
     bold
    0.15
    arrow
    0.15
    olt
    0.15
     Contact
    0.14
     reg
    0.14
    Act Density 0.322%

    No Known Activations