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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences emphasizing the significance or impact of something

    oai_token-act-pair · gpt-3.5-turbo

    the presence of descriptions and attributes of small, fictional creatures or Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptives
    -0.78
    apons
    -0.76
    ©¶æ
    -0.76
    £ı
    -0.75
    manship
    -0.71
    brids
    -0.69
    llor
    -0.69
    Frames
    -0.67
    ivalry
    -0.67
    oust
    -0.67
    POSITIVE LOGITS
    gie
    1.30
     chunk
    1.07
     mistake
    1.00
    oted
    0.96
     deal
    0.95
     difference
    0.94
     misconception
    0.91
    gest
    0.91
     disappointment
    0.90
     understatement
    0.89
    Act Density 0.083%

    No Known Activations