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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply suggestions or invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.77
     Efq
    -0.74
    ristiano
    -0.73
    WireFormatLite
    -0.72
     palvel
    -0.68
     Krakowie
    -0.68
     nguyễn
    -0.67
     objectMapper
    -0.67
     Hampden
    -0.65
     Sist
    -0.64
    POSITIVE LOGITS
     lets
    1.08
    Lets
    0.98
     let
    0.92
     Lets
    0.88
     try
    0.81
     start
    0.77
     take
    0.75
     make
    0.74
     see
    0.71
     keep
    0.68
    Act Density 0.033%

    No Known Activations