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

    Neuronpedia

    INDEX
    Explanations

    words related to endorsing or supporting someone or something

    oai_token-act-pair · gpt-3.5-turbo

    positive affirmations or statements of support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.81
    advertising
    -0.79
    è£ħ
    -0.78
     guiActiveUn
    -0.78
    FactoryReloaded
    -0.72
    ļéĨĴ
    -0.71
    ģĸ
    -0.70
    byss
    -0.69
    %:
    -0.67
    agi
    -0.67
    POSITIVE LOGITS
     but
    1.18
     yes
    1.00
     too
    0.93
     albeit
    0.90
     yeah
    0.88
     though
    0.85
     however
    0.84
     whereas
    0.82
     and
    0.82
     huh
    0.81
    Act Density 0.393%

    No Known Activations