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

    Neuronpedia

    INDEX
    Explanations

    words related to the intensity of emotions or exclamations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.67
    ########.
    -0.58
    WriteTagHelper
    -0.55
     tocado
    -0.51
     incomplète
    -0.48
    flink
    -0.48
    AndPassword
    -0.48
    Bash
    -0.47
    ScreenState
    -0.47
    Климат
    -0.47
    POSITIVE LOGITS
     kasarigan
    0.71
    istic
    0.53
     Parenthood
    0.50
    DataAnnotations
    0.49
    
    0.48
    naf
    0.48
    ündig
    0.47
    Managed
    0.47
    tighets
    0.46
    mab
    0.44
    Act Density 0.455%

    No Known Activations