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

    Neuronpedia

    INDEX
    Explanations

    references to affection or familiarity, particularly in the context of relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oken
    -0.15
    ropic
    -0.13
    rical
    -0.13
    .INSTANCE
    -0.13
     RaisePropertyChanged
    -0.13
    åª
    -0.13
    441
    -0.13
     Burl
    -0.13
    rias
    -0.13
    .amazon
    -0.13
    POSITIVE LOGITS
     dear
    0.38
    Dear
    0.32
     Dear
    0.30
     fellow
    0.25
     reader
    0.23
     friends
    0.22
    Friends
    0.22
     доÑĢог
    0.21
     ladies
    0.20
     Fellow
    0.20
    Act Density 0.127%

    No Known Activations