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

    Neuronpedia

    INDEX
    Explanations

    words related to replacing or being replaced

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substitution or replacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.80
    nex
    -0.79
     therap
    -0.76
    =\"
    -0.76
     redes
    -0.73
    pmwiki
    -0.73
    artment
    -0.72
     helicop
    -0.72
    ombat
    -0.71
    izoph
    -0.71
    POSITIVE LOGITS
     teammate
    1.32
     Mike
    1.22
     Kevin
    1.22
     Dennis
    1.20
     Reggie
    1.20
     Aaron
    1.20
     Chris
    1.19
     fellow
    1.18
     Jamie
    1.18
     Derrick
    1.16
    Act Density 0.211%

    No Known Activations