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

    Neuronpedia

    INDEX
    Explanations

    phrases describing quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers or adjectives that convey large quantities or significant amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tags
    -0.72
    lees
    -0.71
    forums
    -0.71
    tails
    -0.66
    sites
    -0.65
    NetMessage
    -0.63
    hots
    -0.63
     transitions
    -0.62
     buttons
    -0.62
    pins
    -0.62
    POSITIVE LOGITS
     84
    1.06
     158
    1.05
     87
    1.05
     83
    1.04
     85
    1.04
     163
    1.03
     86
    1.03
     68
    1.03
     660
    1.02
     138
    1.02
    Act Density 0.148%

    No Known Activations