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

    Neuronpedia

    INDEX
    Explanations

    phrases related to direct interaction or confrontation between entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unsu
    -0.65
     resemb
    -0.63
     overlooking
    -0.63
     banners
    -0.62
     lacking
    -0.62
     exceptions
    -0.59
     stricken
    -0.59
    Ĥª
    -0.58
     outl
    -0.56
     bundles
    -0.56
    POSITIVE LOGITS
    ilet
    1.18
    pping
    1.05
    othy
    0.93
    pped
    0.93
    bsite
    0.86
    ber
    0.86
    plane
    0.85
    ffee
    0.83
    ggles
    0.82
    ast
    0.81
    Act Density 0.025%

    No Known Activations