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

    Neuronpedia

    INDEX
    Explanations

    the word "her" with different suffixes and contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or a character named "her."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.65
    ãĥ³ãĤ¸
    -0.63
    aredevil
    -0.62
    CCC
    -0.60
     stret
    -0.59
     Glou
    -0.59
    aepernick
    -0.58
     curfew
    -0.58
     sock
    -0.57
     Strauss
    -0.57
    POSITIVE LOGITS
    itage
    1.48
    tz
    1.21
    ding
    1.01
    itance
    1.01
    mite
    0.99
    pes
    0.98
    jee
    0.97
    ald
    0.96
    apy
    0.94
    rha
    0.89
    Act Density 0.024%

    No Known Activations