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

    Neuronpedia

    INDEX
    Explanations

    phrases related to filling spaces or gaps

    oai_token-act-pair · gpt-3.5-turbo

    elements related to filling gaps or roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.69
    edu
    -0.68
    conduct
    -0.67
    rules
    -0.67
    saf
    -0.66
    peer
    -0.65
     Torment
    -0.64
     Kling
    -0.63
    successful
    -0.61
    xual
    -0.61
    POSITIVE LOGITS
     coffers
    1.32
     gap
    0.96
     gaps
    0.93
     niche
    0.90
     vacancy
    0.89
     pores
    0.88
     ranks
    0.85
     brim
    0.82
     void
    0.78
     vacancies
    0.78
    Act Density 0.110%

    No Known Activations