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

    Neuronpedia

    INDEX
    Explanations

    phrases related to publishing or media dissemination

    oai_token-act-pair · gpt-3.5-turbo

    the word "press" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cknowled
    -0.68
     Sheldon
    -0.67
    ARP
    -0.65
     Peninsula
    -0.65
     Syd
    -0.63
    ISO
    -0.63
    ilater
    -0.61
     Scotia
    -0.61
     afore
    -0.58
     classmate
    -0.58
    POSITIVE LOGITS
    press
    1.25
    Press
    1.04
    ions
    0.99
    ure
    0.96
    edIn
    0.91
    gerald
    0.91
    ures
    0.90
    ivity
    0.86
    ername
    0.85
    lict
    0.85
    Act Density 0.016%

    No Known Activations