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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to people in various contexts

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

    Follows a personal pronoun and a verb

    np_acts-logits-general · gemini-2.0-flash

    doing or accomplished actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consultato
    -0.53
    ধ
    -0.47
    arischen
    -0.47
    SerializedSize
    -0.47
    PROLOG
    -0.46
    الإنجليزية
    -0.45
    PrivateKey
    -0.44
    Биография
    -0.43
     zosta
    -0.43
    водства
    -0.43
    POSITIVE LOGITS
     doing
    1.10
    doing
    1.08
    Doing
    1.06
     done
    1.03
     Doing
    1.01
     CreateTagHelper
    0.95
     doin
    0.94
     accomplish
    0.94
     accomplished
    0.93
     DOING
    0.92
    Act Density 0.198%

    No Known Activations