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

    Neuronpedia

    INDEX
    Explanations

    emotional responses or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.97
    ########.
    -0.92
     الحره
    -0.90
    ItemBackground
    -0.89
    sizeCache
    -0.88
     Савезне
    -0.86
     Meksiku
    -0.85
     nahilalakip
    -0.85
    LookAnd
    -0.84
     ujednoznacz
    -0.83
    POSITIVE LOGITS
     Top
    0.53
     S
    0.51
     G
    0.50
    Top
    0.49
    <eos>
    0.49
     top
    0.49
     B
    0.48
     C
    0.47
     F
    0.47
     N
    0.47
    Act Density 0.370%

    No Known Activations