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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate preferences or actions related to personal hobbies or habits

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express actions prefaced by "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Settlement
    -0.65
    ratulations
    -0.65
     clearance
    -0.61
    era
    -0.60
    river
    -0.60
    inguished
    -0.59
     Everest
    -0.58
     sterling
    -0.58
     Nationwide
    -0.58
     yielded
    -0.58
    POSITIVE LOGITS
     speculate
    1.10
     remind
    1.07
     pretend
    1.02
     tease
    1.01
     think
    1.01
     hear
    0.99
     visualize
    0.97
     imagine
    0.97
     joke
    0.95
     see
    0.94
    Act Density 0.052%

    No Known Activations