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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing negative comparisons

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

    worst case scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟬
    -0.80
    iibo
    -0.66
     transfieras
    -0.64
    phrag
    -0.63
    featureID
    -0.63
    transQ
    -0.59
    modelBuilder
    -0.58
     iPads
    -0.58
    PageModule
    -0.58
     Blades
    -0.58
    POSITIVE LOGITS
    worst
    1.05
    worse
    1.02
    Worse
    1.00
    Worst
    1.00
     worse
    0.98
     worst
    0.97
     Worse
    0.94
     Worst
    0.91
     peores
    0.83
     pior
    0.77
    Act Density 0.010%

    No Known Activations