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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or signing up for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking action or urging action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kered
    -0.75
    >[
    -0.74
    orned
    -0.72
    anus
    -0.71
    oxide
    -0.69
    aml
    -0.68
     fault
    -0.68
     apologies
    -0.67
    perm
    -0.67
    serv
    -0.66
    POSITIVE LOGITS
     Tracker
    0.81
     Coordinator
    0.79
     Report
    0.77
    !:
    0.74
     Funding
    0.73
    !,
    0.73
     Volunteers
    0.72
     Unleashed
    0.72
     Role
    0.72
     GOODMAN
    0.71
    Act Density 0.028%

    No Known Activations