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

    Neuronpedia

    INDEX
    Explanations

    phrases related to travel destinations

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     involuntary
    -0.79
     defe
    -0.78
     biological
    -0.77
     agent
    -0.74
     legally
    -0.73
     embedded
    -0.72
     pseudonym
    -0.71
     sue
    -0.70
     biologically
    -0.70
     blasp
    -0.69
    POSITIVE LOGITS
     Depending
    1.18
     Meanwhile
    1.13
     Fortunately
    1.11
     Luckily
    1.09
     Thankfully
    1.08
     Afterwards
    1.07
     Typically
    1.04
     Residents
    1.04
     During
    1.03
     Each
    1.02
    Act Density 0.664%

    No Known Activations