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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strengthening or influencing a situation or outcome

    oai_token-act-pair · gpt-3.5-turbo

    verbs and terms related to inflation, fiscal policy, and economic actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wont
    -0.88
     glances
    -0.69
     characteristic
    -0.67
     buzzing
    -0.66
     clenched
    -0.65
     jokes
    -0.63
     usual
    -0.63
     nightly
    -0.63
     weep
    -0.63
     crawling
    -0.62
    POSITIVE LOGITS
    escal
    1.04
    orpor
    1.02
    establish
    0.96
    idding
    0.95
    activate
    0.95
    rave
    0.95
    ablish
    0.95
    ibr
    0.93
    ilaterally
    0.92
    ranch
    0.91
    Act Density 0.171%

    No Known Activations