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

    Neuronpedia

    INDEX
    Explanations

    references to things or people that are missing

    oai_token-act-pair · gpt-3.5-turbo

    references to missing people or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pub
    -0.75
    advertisement
    -0.69
    idal
    -0.67
    Ru
    -0.66
    OPE
    -0.65
    RET
    -0.65
    rid
    -0.63
     Jinping
    -0.63
     exec
    -0.63
    gard
    -0.63
    POSITIVE LOGITS
     Missing
    0.90
    pelled
    0.81
    ãģı
    0.76
    icit
    0.74
     limbs
    0.74
    missing
    0.73
    itives
    0.73
     411
    0.70
    pelling
    0.70
     orphans
    0.67
    Act Density 0.012%

    No Known Activations