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

    Neuronpedia

    INDEX
    Explanations

    phrases related to benefits, improvements, and achieving favorable outcomes

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

    followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    obtained or achieved benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.57
     lest
    -0.53
    }{*}{
    -0.50
    WhereInput
    -0.47
    )')
    -0.47
    ())));
    -0.46
    vka
    -0.45
    Hentet
    -0.45
     AppColors
    -0.44
    ecake
    -0.44
    POSITIVE LOGITS
     when
    0.96
     adopting
    0.80
     if
    0.78
    when
    0.74
     wanneer
    0.74
     путем
    0.72
     když
    0.68
     khi
    0.68
     using
    0.68
     doing
    0.67
    Act Density 0.751%

    No Known Activations