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

    Neuronpedia

    INDEX
    Explanations

    situations or scenarios involving societal issues and concerns

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods, indicating sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.72
    ither
    -0.69
     agent
    -0.69
     cellar
    -0.69
     withdraw
    -0.68
     dep
    -0.67
    ©¶æ
    -0.67
     pocket
    -0.66
     probation
    -0.65
     ally
    -0.65
    POSITIVE LOGITS
     Especially
    1.24
     Whether
    1.21
     Often
    1.19
     Thankfully
    1.16
     Typically
    1.14
     Particularly
    1.12
     Fortunately
    1.11
     Unfortunately
    1.11
     Luckily
    1.11
     Usually
    1.09
    Act Density 0.464%

    No Known Activations