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

    Neuronpedia

    INDEX
    Explanations

    expressions about desire or willingness for something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intent related to wanting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eda
    -0.64
    Å
    -0.61
    dos
    -0.61
     sweep
    -0.60
    itzer
    -0.60
    Y
    -0.59
    %%
    -0.58
     Dome
    -0.58
    late
    -0.56
    hov
    -0.55
    POSITIVE LOGITS
     wanting
    3.67
     needing
    2.12
     wishing
    2.03
     liking
    1.63
     preferring
    1.53
     intending
    1.51
     hating
    1.47
     lacking
    1.42
     longing
    1.34
     craving
    1.32
    Act Density 0.011%

    No Known Activations