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

    Neuronpedia

    INDEX
    Explanations

    phrases related to change or progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sequence or course of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.82
    fml
    -0.75
    ingers
    -0.74
    paces
    -0.72
    kernel
    -0.72
    tops
    -0.71
    iaries
    -0.68
    wives
    -0.67
    chens
    -0.66
    sense
    -0.66
    POSITIVE LOGITS
     events
    1.18
     development
    1.14
     progression
    1.13
     elimination
    1.12
     evolution
    1.10
     advancement
    1.03
     succession
    1.02
     action
    0.99
     escalation
    0.98
     accumulation
    0.97
    Act Density 0.116%

    No Known Activations