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

    Neuronpedia

    INDEX
    Explanations

    phrases conveying honesty and sincerity

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

    Honest or sincere statements and declarations

    np_acts-logits-general · gemini-2.0-flash

    insincere results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pushFollow
    -0.61
     O
    -0.58
    RegistryLite
    -0.55
     Cal
    -0.54
    Jegyzetek
    -0.54
    ˈ
    -0.54
    __).
    -0.52
     disponibilités
    -0.52
     lenker
    -0.51
     Giordano
    -0.51
    POSITIVE LOGITS
     ་་
    0.95
     honest
    0.89
    Honest
    0.89
    honest
    0.82
     ―――――
    0.81
     honestly
    0.79
     Honest
    0.78
     ehrlich
    0.76
     raiſ
    0.75
     sincere
    0.71
    Act Density 0.090%

    No Known Activations