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

    Neuronpedia

    INDEX
    Explanations

    time periods or dates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" and related phrases indicating time or a range

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Planet
    -0.63
    java
    -0.62
    earable
    -0.61
    xual
    -0.61
    riad
    -0.60
    framework
    -0.59
    ourke
    -0.57
    Entity
    -0.57
    utenberg
    -0.56
    erman
    -0.56
    POSITIVE LOGITS
     December
    1.28
     June
    1.27
     April
    1.27
     October
    1.27
     September
    1.26
     March
    1.26
     August
    1.24
     July
    1.22
     February
    1.20
     November
    1.19
    Act Density 0.047%

    No Known Activations