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

    Neuronpedia

    INDEX
    Explanations

    contrastive discourse markers indicating a shift in the argument or point of view

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

    contrast conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.53
    AutoScaleMode
    -0.53
    :✨
    -0.48
     Meksiku
    -0.47
    /**
    -0.46
    WaitGroup
    -0.46
     referrerpolicy
    -0.46
     noDo
    -0.43
    StoryboardSegue
    -0.42
     betweenstory
    -0.41
    POSITIVE LOGITS
    LabelTagHelper
    0.40
    round
    0.38
    rund
    0.38
     afstand
    0.37
     diting
    0.35
    randall
    0.35
    aguya
    0.35
    mist
    0.35
    plex
    0.35
    replaceable
    0.35
    Act Density 0.284%

    No Known Activations