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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.85
     quæ
    -0.77
     ſtate
    -0.76
     houſe
    -0.71
     habet
    -0.71
     ſen
    -0.68
     tarko
    -0.65
    ſelf
    -0.63
     difp
    -0.62
     ſch
    -0.62
    POSITIVE LOGITS
    adpleegd
    0.82
    /#{
    0.75
     "..\..\
    0.74
    thâu
    0.74
    +#+
    0.74
    mphony
    0.73
    GOTREF
    0.71
     THAN
    0.70
    #+#
    0.69
    :+:
    0.66
    Act Density 0.178%

    No Known Activations