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

    Neuronpedia

    INDEX
    Explanations

    words that are closely related to the prefix "er"

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "er" often related to roles, professions, or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.72
    atown
    -0.71
     Crowd
    -0.68
    quez
    -0.68
     Marketable
    -0.67
    oaded
    -0.67
     Hatch
    -0.65
    atham
    -0.65
     Partnership
    -0.64
    cox
    -0.63
    POSITIVE LOGITS
     er
    3.73
     erase
    1.41
     Er
    1.38
    Er
    1.36
     erased
    1.35
     err
    1.22
     um
    1.19
     erosion
    1.18
     uh
    1.15
     eroded
    1.07
    Act Density 0.011%

    No Known Activations