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

    Neuronpedia

    INDEX
    Explanations

    phrases that express conditional or comparative relationships

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

    "As" followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    as followed by pronouns or reporting verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vPvB
    -0.68
     convertView
    -0.66
    WithMany
    -0.61
    routeProvider
    -0.61
    HostException
    -0.60
    didSet
    -0.60
    ObjectContext
    -0.59
    łaszcza
    -0.59
    IConfiguration
    -0.58
    (!__
    -0.58
    POSITIVE LOGITS
     per
    0.93
     earlier
    0.60
     stated
    0.60
     vroeg
    0.53
     conformidad
    0.53
     told
    0.52
    earlier
    0.50
     said
    0.50
     there
    0.50
     gevolg
    0.50
    Act Density 0.109%

    No Known Activations