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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate typical or characteristic features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hunger
    -0.15
     Bod
    -0.15
    edm
    -0.14
    ibur
    -0.14
    çĦ¦
    -0.14
    оÑĥ
    -0.14
    ary
    -0.14
    vp
    -0.14
    онÑĮ
    -0.14
    wig
    -0.14
    POSITIVE LOGITS
    ity
    0.24
    mente
    0.21
    ITY
    0.19
     xuyên
    0.17
    cy
    0.17
    ities
    0.17
    ily
    0.17
    cies
    0.16
    -looking
    0.15
    weise
    0.15
    Act Density 0.043%

    No Known Activations