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

    Neuronpedia

    INDEX
    Explanations

    female names and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jr
    -0.23
    jr
    -0.20
     JR
    -0.19
     jr
    -0.18
    JR
    -0.17
     himself
    -0.17
    -0.16
     Junior
    -0.15
    romatic
    -0.15
    zew
    -0.15
    POSITIVE LOGITS
     herself
    0.26
    /he
    0.17
     Anne
    0.16
    pector
    0.15
     Augusta
    0.15
     могла
    0.15
    athed
    0.15
    Ann
    0.15
    affer
    0.15
     Carolina
    0.15
    Act Density 0.182%

    No Known Activations