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

    Neuronpedia

    INDEX
    Explanations

    words related to achieving success or victory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pores
    -0.72
    pper
    -0.70
    pta
    -0.70
     contrace
    -0.69
    lder
    -0.68
     compuls
    -0.65
     vitro
    -0.63
     groceries
    -0.62
    lde
    -0.61
     consultation
    -0.61
    POSITIVE LOGITS
    antly
    1.50
    alist
    1.26
    s
    1.08
    antes
    1.01
    eous
    0.97
    ivals
    0.95
    al
    0.95
    ant
    0.94
    ION
    0.90
    shire
    0.87
    Act Density 0.008%

    No Known Activations