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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permissions, decisions, and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -0.55
     dólar
    -0.51
     designs
    -0.51
     zircon
    -0.47
     NgModule
    -0.46
    jenigen
    -0.45
    designs
    -0.44
    glColor
    -0.43
    gitte
    -0.43
    __':
    -0.43
    POSITIVE LOGITS
    +#+#
    0.81
    Diweddarwch
    0.74
     Dette
    0.68
     ويكيپيديا
    0.63
     happen
    0.62
    basicConfig
    0.62
    Esto
    0.61
    usiai
    0.61
    DebuggerNonUser
    0.61
    ViewImports
    0.61
    Act Density 0.452%

    No Known Activations