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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     = 
    -0.76
    
    -0.62
    ;-)
    -0.62
    ]-->
    -0.61
    CGRectMake
    -0.57
     ;-)
    -0.56
    esomeness
    -0.55
     Aws
    -0.55
    :-)
    -0.54
    冏
    -0.54
    POSITIVE LOGITS
     🥺
    0.84
     idk
    0.81
     ngl
    0.78
    ptid
    0.75
    🥺
    0.75
     lmao
    0.74
     tbh
    0.73
     Idk
    0.70
     😭😭
    0.70
     abt
    0.70
    Act Density 0.142%

    No Known Activations