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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to finish" and references to lakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     laſſen
    -1.54
    <unused52>
    -1.54
    <unused16>
    -1.53
    <unused79>
    -1.53
    <unused8>
    -1.53
    [@BOS@]
    -1.53
    <unused17>
    -1.52
    <unused23>
    -1.52
    <unused14>
    -1.52
    <unused3>
    -1.52
    POSITIVE LOGITS
    '
    1.09
     
    0.84
    1
    0.74
    3
    0.68
    0
    0.68
    4
    0.64
    2
    0.63
    7
    0.62
    5
    0.60
    8
    0.59
    Act Density 0.103%

    No Known Activations