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

    Neuronpedia

    INDEX
    Explanations

    references to expressions of disappointment or criticism

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

    lamentiing words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.54
     GenerationType
    -0.54
    AnchorStyles
    -0.50
    ſelves
    -0.49
    ExtendWith
    -0.49
     dynamite
    -0.49
     encre
    -0.48
     toothbrush
    -0.47
    cherichia
    -0.47
    InjectAttribute
    -0.47
    POSITIVE LOGITS
     lament
    1.13
     lamented
    1.13
     lamenta
    0.93
     Lament
    0.87
     celebrating
    0.66
    lament
    0.66
     lamentable
    0.65
     dismayed
    0.59
     complaining
    0.58
     Celebrating
    0.58
    Act Density 0.010%

    No Known Activations