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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating employment terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Terms
    -0.16
    terms
    -0.16
    osl
    -0.15
    Terms
    -0.15
    stadt
    -0.15
    ause
    -0.14
     terms
    -0.14
    onz
    -0.14
    term
    -0.14
    çĶ
    -0.14
    POSITIVE LOGITS
     respect
    0.31
     connection
    0.30
     Connection
    0.24
    connection
    0.21
     light
    0.20
     Respect
    0.20
     оÑĤноÑĪ
    0.20
     CONNECTION
    0.20
    _connection
    0.20
    nection
    0.19
    Act Density 0.245%

    No Known Activations