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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with measurements or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyph
    -0.16
     eldre
    -0.15
    mts
    -0.15
    tw
    -0.15
    gba
    -0.14
    cus
    -0.14
    rch
    -0.14
    öy
    -0.14
    ascar
    -0.14
    asure
    -0.14
    POSITIVE LOGITS
     Esper
    0.32
     Ä
    0.31
     esper
    0.26
    Ä
    0.25
     Å
    0.23
     estas
    0.23
    Å
    0.22
     kun
    0.20
     la
    0.20
     mall
    0.20
    Act Density 0.001%

    No Known Activations