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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to approval and disapproval ratings

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

    approval or disapproval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     newOwner
    -0.55
     Administrativna
    -0.55
    tvguidetime
    -0.54
     âgé
    -0.53
    DotNetBar
    -0.50
    BackStack
    -0.50
    //
    -0.49
    RunWith
    -0.49
    DockStyle
    -0.49
    /*
    -0.48
    POSITIVE LOGITS
     disapproval
    0.47
     approves
    0.46
     approval
    0.46
     liked
    0.43
     Approval
    0.40
    Liked
    0.40
    Approval
    0.39
     disappro
    0.39
    我喜欢
    0.39
     liking
    0.39
    Act Density 0.059%

    No Known Activations