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

    Neuronpedia

    INDEX
    Explanations

    monetary amounts and their contextual references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antar
    -0.19
    rement
    -0.18
    Dummy
    -0.15
    usercontent
    -0.15
    tein
    -0.15
    аÑĢаÑĤ
    -0.14
    amma
    -0.14
    anzeigen
    -0.14
    lyph
    -0.14
    opi
    -0.14
    POSITIVE LOGITS
     Dillon
    0.16
     ge
    0.16
    pat
    0.15
     Lakes
    0.15
     Gap
    0.15
    kap
    0.14
     either
    0.14
     mind
    0.14
     tro
    0.14
    0.14
    Act Density 0.022%

    No Known Activations