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

    Neuronpedia

    INDEX
    Explanations

    contractions and their associated phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.71
    TemporalType
    -0.62
    \{\\
    -0.62
    featureID
    -0.62
     ſind
    -0.59
    Хьажоргаш
    -0.57
    !*\
    -0.55
     NSError
    -0.55
    :✨
    -0.54
     FetchType
    -0.54
    POSITIVE LOGITS
    ould
    0.50
    have
    0.50
    ere
    0.49
    think
    0.49
    rt
    0.49
    lieve
    0.49
    he
    0.47
    hat
    0.47
    n
    0.46
    tually
    0.45
    Act Density 0.379%

    No Known Activations