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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing negativity or dissatisfaction

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

    Expressing urgent need or importance

    np_acts-logits-general · gemini-2.0-flash

    urgently or desperately needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Expect
    -0.50
    [])
    -0.50
    ritz
    -0.49
    >[]
    -0.49
     wonderful
    -0.48
     intend
    -0.48
    expect
    -0.48
     expect
    -0.47
    []=
    -0.46
    ESCO
    -0.46
    POSITIVE LOGITS
     urgently
    1.18
     desperately
    1.04
     urgente
    1.02
     ASAP
    1.01
     badly
    0.98
     desesper
    0.96
    ValueStyle
    0.95
     asap
    0.94
     dringend
    0.91
     preferably
    0.89
    Act Density 0.282%

    No Known Activations