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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "mand" and its associated forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ased
    -0.16
    ahren
    -0.15
    aqu
    -0.15
    mediate
    -0.15
    idar
    -0.15
    a
    -0.15
    asts
    -0.14
    sand
    -0.14
    indre
    -0.14
    idia
    -0.14
    POSITIVE LOGITS
    arin
    0.28
    ATORY
    0.24
    olin
    0.22
    ev
    0.20
     Mand
    0.20
    rels
    0.20
    itory
    0.20
    amus
    0.18
    elay
    0.18
    eb
    0.17
    Act Density 0.006%

    No Known Activations