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

    Neuronpedia

    INDEX
    Explanations

    words related to hiring or employment

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles used as nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scales
    -0.73
     dwar
    -0.67
     Ll
    -0.65
     rh
    -0.65
     marg
    -0.65
     outl
    -0.64
     zo
    -0.61
     bullies
    -0.61
     Ka
    -0.61
     pudding
    -0.60
    POSITIVE LOGITS
    iring
    4.37
    ired
    2.50
    ires
    2.49
    IRED
    1.89
    ire
    1.84
    irement
    1.66
    iry
    1.63
    irements
    1.63
    irable
    1.63
    iries
    1.40
    Act Density 0.006%

    No Known Activations