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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and their usage in context

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

    Contractions with "will" or "shall"

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by future action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.67
    oneofs
    -0.63
    Diweddarwch
    -0.58
     olisi
    -0.57
     ProtoMessage
    -0.55
    alamus
    -0.53
    XmlIgnore
    -0.53
    seamnă
    -0.52
     tulee
    -0.51
    jamientos
    -0.51
    POSITIVE LOGITS
     ill
    1.11
     Ill
    1.07
     ll
    0.92
    Ill
    0.92
    ill
    0.88
     ILL
    0.81
    ’
    0.79
     il
    0.76
     Il
    0.73
    Il
    0.67
    Act Density 0.124%

    No Known Activations