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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "der" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antis
    -0.71
     liberties
    -0.70
    anwhile
    -0.69
    justice
    -0.67
    ees
    -0.67
    alian
    -0.65
    ioned
    -0.63
     apprehens
    -0.63
    ilton
    -0.62
    iao
    -0.61
    POSITIVE LOGITS
    ��
    0.74
    pri
    0.67
    ��
    0.66
     Scor
    0.64
    pictured
    0.62
     certs
    0.61
    massive
    0.61
    �
    0.60
    qv
    0.60
     RH
    0.59
    Act Density 0.017%

    No Known Activations