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

    Neuronpedia

    INDEX
    Explanations

    terms relating to destruction or tearing into pieces

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of shredding, both literally and metaphorically

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.76
    emis
    -0.63
    amide
    -0.62
    ioch
    -0.61
    juven
    -0.61
     presiding
    -0.61
     Ple
    -0.61
    EGA
    -0.61
     Gard
    -0.60
     Swords
    -0.60
    POSITIVE LOGITS
    ding
    1.37
     shred
    1.12
    aby
    1.01
    sburg
    0.97
    der
    0.97
    itionally
    0.94
    ulously
    0.93
    nuts
    0.90
    lings
    0.87
    ming
    0.87
    Act Density 0.007%

    No Known Activations