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

    Neuronpedia

    INDEX
    Explanations

    words related to liking or preferences, especially in the context of engagement with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    like and dislikes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DispatchToProps
    -0.51
    modelBuilder
    -0.46
    orianCalendar
    -0.45
    unnitel
    -0.44
    mockMvc
    -0.44
    DockStyle
    -0.44
    rakech
    -0.43
    IntoConstraints
    -0.43
    iconductor
    -0.42
    zeß
    -0.42
    POSITIVE LOGITS
    Likes
    1.06
    likes
    0.99
     Likes
    0.93
     likes
    0.89
    Liked
    0.84
     лай
    0.71
     LIKE
    0.66
    Like
    0.65
    Dislikes
    0.65
    liked
    0.63
    Act Density 0.013%

    No Known Activations