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

    Neuronpedia

    INDEX
    Explanations

    topics related to cultural and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nues
    -0.17
    @student
    -0.16
    asaki
    -0.15
    ukes
    -0.15
    iyon
    -0.15
    .react
    -0.15
    unda
    -0.14
    NEL
    -0.14
     Jo
    -0.14
    bage
    -0.14
    POSITIVE LOGITS
     such
    0.37
    such
    0.30
     like
    0.27
     likes
    0.24
     including
    0.24
    :
    0.23
     SUCH
    0.21
     include
    0.20
     Such
    0.19
    å¦Ĥ
    0.19
    Act Density 0.102%

    No Known Activations