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

    Neuronpedia

    INDEX
    Explanations

    instances of agreement and expressions of consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Corpor
    -0.14
     outgoing
    -0.14
    ahy
    -0.14
    otec
    -0.14
     analog
    -0.14
     liken
    -0.14
    oho
    -0.14
    ubb
    -0.13
     Clifford
    -0.13
    olic
    -0.13
    POSITIVE LOGITS
     agrees
    0.23
     Agree
    0.22
     conc
    0.21
     agree
    0.21
    åIJĮæĦı
    0.20
     agreement
    0.19
     agreeing
    0.19
    agree
    0.19
     Agreement
    0.17
    Echo
    0.16
    Act Density 0.289%

    No Known Activations