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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or relation between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »¿
    -2.28
    ¬
    -2.27
    «
    -2.18
    Īĺ
    -2.11
    Ĺ
    -2.02
    ĭ
    -1.96
    ij
    -1.95
    ł
    -1.94
    Ĥ
    -1.92
    ¤
    -1.86
    POSITIVE LOGITS
    enstein
    1.89
    minist
    1.72
    grounds
    1.63
    noon
    1.56
    ovir
    1.56
    ball
    1.55
    stock
    1.51
    oso
    1.50
    ivir
    1.48
    older
    1.45
    Act Density 0.063%

    No Known Activations