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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating accompaniment or support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yles
    -0.16
    URED
    -0.15
    lings
    -0.15
    idual
    -0.14
    away
    -0.14
     Avery
    -0.14
    agar
    -0.14
    :async
    -0.14
    dle
    -0.14
    idget
    -0.14
    POSITIVE LOGITS
     accompany
    0.27
     accompanied
    0.23
     accompanies
    0.23
     accompanying
    0.23
    ä¼´
    0.20
     escort
    0.18
    /support
    0.18
     escorts
    0.17
     accompagn
    0.17
     closely
    0.17
    Act Density 0.015%

    No Known Activations