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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to interests, particularly in legal and custody contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovu
    -0.16
    enko
    -0.16
    itta
    -0.15
    ìĨ
    -0.15
    eba
    -0.15
    elm
    -0.15
    onna
    -0.15
    ula
    -0.14
    оÑĢоÑĤ
    -0.14
    uel
    -0.14
    POSITIVE LOGITS
     interests
    0.45
    interest
    0.32
     interest
    0.28
     interes
    0.27
     Interest
    0.23
     инÑĤеÑĢеÑģ
    0.23
     interess
    0.23
     interesse
    0.21
    best
    0.21
     interested
    0.21
    Act Density 0.121%

    No Known Activations