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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achievements and affiliations, especially in sports and education

    oai_token-act-pair · gpt-3.5-turbo

    numerals and punctuation marks, particularly at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     optional
    -0.81
     explan
    -0.73
    pport
    -0.72
     nodd
    -0.69
     gau
    -0.66
     consolation
    -0.65
     dynamically
    -0.65
     asymm
    -0.65
     ecosystem
    -0.64
     stamped
    -0.63
    POSITIVE LOGITS
     During
    1.38
     Afterwards
    1.37
     Later
    1.32
     His
    1.29
     He
    1.25
     Shortly
    1.24
     Eventually
    1.21
     Prior
    1.19
     Before
    1.16
     After
    1.16
    Act Density 0.236%

    No Known Activations