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

    Neuronpedia

    INDEX
    Explanations

    phrases related to offering support or services to clients and businesses

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

    followed by modal verbs

    np_acts-logits-general · gemini-2.0-flash

    will or could followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esposo
    -0.90
     magasiner
    -0.87
     flavorful
    -0.87
    AVOR
    -0.83
     honors
    -0.82
    ômico
    -0.81
    dized
    -0.77
     neighborhood
    -0.77
    Neighbors
    -0.77
     favorably
    -0.77
    POSITIVE LOGITS
    Whilst
    1.85
     Whilst
    1.78
     whilst
    1.61
    initialise
    1.35
    Firstly
    1.21
     Firstly
    1.14
     specialises
    1.11
     realising
    1.11
     realises
    1.10
     realise
    1.10
    Act Density 0.732%

    No Known Activations