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

    Neuronpedia

    INDEX
    Explanations

    pronouns denoting possession and references to female characters

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

    Sentences starting with "She" or "Her"

    np_acts-logits-general · gemini-2.0-flash

    she followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     himself
    -0.63
    Completo
    -0.44
     Himself
    -0.44
     occupying
    -0.42
     Raymond
    -0.42
     Maximus
    -0.42
     posX
    -0.41
     balloon
    -0.40
     blow
    -0.40
     boost
    -0.40
    POSITIVE LOGITS
     noastră
    0.57
    ussis
    0.56
     تانيه
    0.54
     CURIAM
    0.54
    Rhestr
    0.52
     Administrativna
    0.52
     uVar
    0.51
     sereia
    0.49
    Parcelize
    0.49
    cherie
    0.48
    Act Density 0.260%

    No Known Activations