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

    Neuronpedia

    INDEX
    Explanations

    words related to carrying out a cause or mission

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.77
    manship
    -0.73
    ed
    -0.72
    ing
    -0.71
    Tang
    -0.64
    ly
    -0.62
    ĸļ
    -0.60
    YA
    -0.60
    edly
    -0.59
     ye
    -0.58
    POSITIVE LOGITS
    ades
    2.27
    ading
    2.06
    aded
    1.96
    aders
    1.89
    ade
    1.75
    asion
    1.59
    ader
    1.53
    ADE
    1.51
    asions
    1.22
    adier
    1.20
    Act Density 0.118%

    No Known Activations