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

    Neuronpedia

    INDEX
    Explanations

    high-frequency common words and phrases that indicate structure or grammar

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     babes
    -0.17
     Leban
    -0.16
    oir
    -0.14
    æµ®
    -0.14
    à¥įतन
    -0.14
    nia
    -0.14
    ancell
    -0.14
    ipel
    -0.14
     Rivers
    -0.13
     srd
    -0.13
    POSITIVE LOGITS
    233
    0.15
     pit
    0.15
     temper
    0.14
    588
    0.14
     trainable
    0.14
    ÂĽ
    0.14
     Tub
    0.13
     Hopkins
    0.13
    inalg
    0.13
    268
    0.13
    Act Density 0.001%

    No Known Activations