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

    Neuronpedia

    INDEX
    Explanations

    phrases related to customer service and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows certain function words (more, are, most)

    np_acts-logits-general · gemini-2.0-flash

    common word followed by specific word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hésite
    -0.66
    NewLabel
    -0.52
    posób
    -0.51
     privilegio
    -0.49
    Adaptor
    -0.48
     vitesses
    -0.47
    VILLA
    -0.47
    <bos>
    -0.47
    তথ্যসূত্র
    -0.46
    eaway
    -0.46
    POSITIVE LOGITS
    bootstrapcdn
    0.62
     kaarangay
    0.61
    хьтан
    0.60
     AssemblyVersion
    0.58
    :')
    0.57
    NamedQueries
    0.56
    '))
    0.56
     (!(
    0.56
     beginnetje
    0.53
    )).
    0.53
    Act Density 0.060%

    No Known Activations