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

    Neuronpedia

    INDEX
    Explanations

    elements that contribute to the depth and richness of descriptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.18
    oton
    -0.15
    engu
    -0.14
    ximity
    -0.14
    arem
    -0.14
    .Master
    -0.14
    obj
    -0.13
    å¥ij
    -0.13
     обÑĢазом
    -0.13
     jspb
    -0.13
    POSITIVE LOGITS
     substance
    0.36
     depth
    0.32
     dimension
    0.30
     personality
    0.30
     character
    0.29
     interest
    0.28
     punch
    0.27
     pz
    0.27
     definition
    0.26
     zip
    0.26
    Act Density 0.314%

    No Known Activations