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

    Neuronpedia

    INDEX
    Explanations

    instances of the sequence "Mar" followed by specific tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pidou
    -0.82
    BibitemShut
    -0.71
    kegaard
    -0.69
     Sigism
    -0.63
     Brems
    -0.63
     препратки
    -0.63
     Asturias
    -0.60
    bibinfo
    -0.60
     enco
    -0.59
     Vek
    -0.59
    POSITIVE LOGITS
     Mar
    3.54
    Mar
    3.32
     mar
    3.22
     MAR
    2.97
    mar
    2.89
    MAR
    2.63
     Maru
    1.87
    Marg
    1.84
     Marr
    1.82
     Мар
    1.81
    Act Density 0.075%

    No Known Activations