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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate possession or relationships between people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    หว
    -0.16
    лиÑĤ
    -0.15
    fone
    -0.15
    fly
    -0.14
    SupportedContent
    -0.14
    xima
    -0.14
    uhn
    -0.14
    ôi
    -0.14
    âĢŀTo
    -0.14
    rimp
    -0.13
    POSITIVE LOGITS
     choice
    0.54
    choice
    0.41
     choosing
    0.41
     Choice
    0.38
    Choice
    0.35
    _choice
    0.35
    -choice
    0.34
     cho
    0.31
     choix
    0.31
     liking
    0.30
    Act Density 0.024%

    No Known Activations