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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate reduction or minimization

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

    cut down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.51
     tabled
    -0.48
    \{\\
    -0.46
    argb
    -0.46
    Dış
    -0.44
     Referential
    -0.44
    께
    -0.43
    richlet
    -0.42
     blij
    -0.41
     kier
    -0.41
    POSITIVE LOGITS
     Down
    0.48
     cutting
    0.47
     shorter
    0.47
     alberi
    0.45
     down
    0.45
     trees
    0.44
     cut
    0.43
    WithMany
    0.41
     econom
    0.40
    Down
    0.40
    Act Density 0.004%

    No Known Activations