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

    Neuronpedia

    INDEX
    Explanations

    entertainment-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ียร
    -0.16
    .lp
    -0.15
     anthrop
    -0.14
    ndon
    -0.14
    Anth
    -0.14
    lesc
    -0.14
    ´:
    -0.14
     Anthrop
    -0.14
     soud
    -0.14
    anth
    -0.13
    POSITIVE LOGITS
    cala
    0.15
    adia
    0.15
    HONE
    0.14
    ucken
    0.14
    äch
    0.14
    pon
    0.14
    ät
    0.14
    achment
    0.14
    erna
    0.13
    gs
    0.13
    Act Density 0.000%

    No Known Activations