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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating methods or approaches to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ington
    -0.19
    kir
    -0.15
    dag
    -0.14
    OnInit
    -0.13
    anca
    -0.13
    INGTON
    -0.13
    ÑĬ
    -0.13
     tắc
    -0.13
    acet
    -0.13
    495
    -0.13
    POSITIVE LOGITS
    zend
    0.16
     opportunity
    0.15
     way
    0.15
    auge
    0.15
    utherford
    0.14
    .jquery
    0.14
    MMdd
    0.14
     Rap
    0.14
    ñana
    0.14
    spender
    0.14
    Act Density 0.030%

    No Known Activations