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

    Neuronpedia

    INDEX
    Explanations

    words related to agreement and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    171
    -0.16
     Meh
    -0.16
    iba
    -0.16
    273
    -0.14
     mú
    -0.14
    234
    -0.14
     Venice
    -0.14
     tslib
    -0.14
     OSC
    -0.14
     Stand
    -0.13
    POSITIVE LOGITS
    piler
    0.16
    jeme
    0.15
    /errors
    0.15
    uster
    0.15
    acas
    0.15
    erset
    0.15
    IELDS
    0.14
    ALES
    0.14
    поÑĩ
    0.14
    licos
    0.14
    Act Density 0.000%

    No Known Activations