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

    Neuronpedia

    INDEX
    Explanations

    words related to dress or dress-related activities

    oai_token-act-pair · gpt-3.5-turbo

    words relating to various forms of "ress" that could indicate roles or portrayals, likely focusing on female characters or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.69
     thence
    -0.66
    lder
    -0.64
     elig
    -0.63
     compan
    -0.63
    obo
    -0.61
     primed
    -0.60
    ccording
    -0.60
     gum
    -0.59
     impacted
    -0.59
    POSITIVE LOGITS
    ions
    1.06
    ively
    1.00
    ional
    0.93
    entials
    0.91
    encer
    0.90
    entially
    0.90
    mann
    0.88
    itect
    0.87
    ãĥĺ
    0.87
    IVE
    0.87
    Act Density 0.008%

    No Known Activations