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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    punctuations, particularly commas and their context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.77
    ozy
    -0.69
    inctions
    -0.67
    zb
    -0.66
    rastructure
    -0.66
    payer
    -0.65
    ãĥīãĥ©
    -0.65
    rak
    -0.64
    unct
    -0.63
    iz
    -0.62
    POSITIVE LOGITS
     hoping
    1.07
     but
    1.05
     joking
    1.05
     lest
    1.02
     reminding
    1.00
     implying
    1.00
     prompting
    0.99
     saying
    0.94
     insisting
    0.93
     pretending
    0.93
    Act Density 0.350%

    No Known Activations