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

    Neuronpedia

    INDEX
    Explanations

    words related to negativity and dissatisfaction

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

    Followed by suffixes

    np_acts-logits-general · gemini-2.0-flash

    describing negative qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -1.10
     purpoſe
    -1.08
     pleaſure
    -1.06
     fubject
    -1.03
     ſtate
    -1.03
     perſon
    -0.99
    出版年
    -0.95
    RenderAtEndOf
    -0.93
     myſelf
    -0.92
    bootstrapcdn
    -0.90
    POSITIVE LOGITS
    umph
    0.43
    Referencias
    0.42
     First
    0.42
     ver
    0.42
     Ersten
    0.41
    [/
    0.41
    outchouc
    0.40
    Ĭ
    0.40
     mis
    0.40
    ingly
    0.39
    Act Density 0.364%

    No Known Activations